© 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. 4198
    Prev
    Next
    INDEX
    Explanations

    phrases that correlate with discussions of assessment and evaluation

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

    words or phrases that come after prepositions like "of," "from," and "in" to identify objects or sources.

    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
     something
    -0.47
     gevol
    -0.45
    一项
    -0.43
     mergeFrom
    -0.41
     is
    -0.41
    something
    -0.41
     Hälfte
    -0.40
    WritableDatabase
    -0.40
     another
    -0.39
    的一种
    -0.39
    POSITIVE LOGITS
     مختلف
    0.83
     various
    0.83
     المختلفة
    0.82
    various
    0.82
    Various
    0.77
     שונים
    0.76
     които
    0.76
     которые
    0.75
     Various
    0.73
     poszczegól
    0.71
    Activations Density 1.052%

    No Known Activations