© 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. 37-GEMMASCOPE-RES-16K
    11. 4841
    Prev
    Next
    INDEX
    Explanations

    terms related to record-keeping and documentation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FunctionFlags
    -0.57
    OGND
    -0.52
    PerformLayout
    -0.50
    期刊论文
    -0.50
    ucksack
    -0.49
     ***!
    -0.49
    RenderAtEndOf
    -0.47
    tanleria
    -0.47
     onPostExecute
    -0.47
    SequentialGroup
    -0.45
    POSITIVE LOGITS
     keep
    3.25
     kept
    3.13
     keeping
    3.09
    keep
    3.05
     Keep
    2.98
    Keep
    2.95
     keeps
    2.94
     KEEP
    2.81
     Keeping
    2.77
    kept
    2.72
    Activations Density 0.596%

    No Known Activations