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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8922
    Prev
    Next
    INDEX
    Explanations

    references to transformations and changes in state or circumstances

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

    words following "but" or appearing in contrasting/adversative contexts.

    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
    elif
    -0.45
     resourceCulture
    -0.42
    WebServlet
    -0.40
     становника
    -0.38
    ngOnInit
    -0.38
    ParallelGroup
    -0.37
    putAll
    -0.36
    PageIndex
    -0.35
    NewReader
    -0.35
    ="@+
    -0.34
    POSITIVE LOGITS
     eventually
    3.50
     ultimately
    3.22
    Eventually
    3.14
     Eventually
    3.14
    eventually
    3.05
     Ultimately
    2.88
     eventual
    2.84
     uiteindelijk
    2.73
    Ultimately
    2.69
     finally
    2.64
    Activations Density 1.644%

    No Known Activations