© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3307
    Prev
    Next
    INDEX
    Explanations

    connections and summarizing results in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    transitional phrases in academic/scientific papers that indicate a conclusion or key finding.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    transitions between sentences or clauses, particularly at punctuation marks and discourse connectors that introduce new findings or results in scientific writing.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.60
    jenige
    -0.55
     Bewußt
    -0.54
    Sklici
    -0.48
    Tē
    -0.48
    jenigen
    -0.46
    aronder
    -0.46
    netinet
    -0.45
     bevor
    -0.45
    featureID
    -0.43
    POSITIVE LOGITS
     Interestingly
    1.05
    Interestingly
    1.02
     interestingly
    0.95
     Surprisingly
    0.81
     Similar
    0.78
    Similar
    0.76
     surprisingly
    0.76
     Notably
    0.75
    Surprisingly
    0.74
    Contrary
    0.74
    Activations Density 1.611%

    No Known Activations