© 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. 20-GEMMASCOPE-RES-16K
    11. 229
    Prev
    Next
    INDEX
    Explanations

    programming-related language constructs and syntax elements

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

    after a variable name or assignment

    np_acts-logits-general · gemini-2.0-flash

    optional fields or possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    metter
    -0.48
    jah
    -0.47
    抱
    -0.47
     Stamps
    -0.47
     aceit
    -0.44
    ]-->
    -0.43
     Attitude
    -0.43
    ='_
    -0.43
    istika
    -0.43
    lebens
    -0.42
    POSITIVE LOGITS
     ModelExpression
    1.03
     may
    1.00
    Nullable
    0.99
     possibly
    0.92
    EDEFAULT
    0.91
     maybe
    0.90
    ?.
    0.86
     might
    0.84
     Maybe
    0.81
     perhaps
    0.81
    Activations Density 0.118%

    No Known Activations