© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 12734
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries about reasoning or explanations behind various phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeText
    -0.64
    цезда
    -0.61
     архивлан
    -0.60
    principalColumn
    -0.58
    Gives
    -0.58
    Means
    -0.56
    Gets
    -0.55
    +#+
    -0.55
     كومونز
    -0.54
    Removes
    -0.54
    POSITIVE LOGITS
     does
    1.93
     are
    1.93
     do
    1.83
     did
    1.78
     is
    1.51
     can
    1.37
    does
    1.29
     am
    1.27
     will
    1.23
     would
    1.23
    Activations Density 0.559%

    No Known Activations