© 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. 7806
    Prev
    Next
    INDEX
    Explanations

    code comments and documentation sections in programming code

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

    Javadoc comments containing "@param"

    np_acts-logits-general · gemini-2.0-flash

    @param or @return documentation

    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
    istoitu
    -0.63
     inher
    -0.49
    fjspx
    -0.46
    <()>
    -0.45
    bid
    -0.45
     {};
    -0.45
     phase
    -0.44
    ้าย
    -0.44
    gram
    -0.43
    cita
    -0.43
    POSITIVE LOGITS
     return
    2.01
     returns
    1.89
    Returns
    1.82
     Returns
    1.79
     Return
    1.76
    return
    1.71
    returns
    1.68
     RETURN
    1.68
    Return
    1.66
     RETURNS
    1.60
    Activations Density 0.207%

    No Known Activations