© 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. 18-GEMMASCOPE-RES-16K
    11. 6401
    Prev
    Next
    INDEX
    Explanations

    warning messages related to coding or server errors

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

    "debug" and file paths

    np_acts-logits-general · gemini-2.0-flash

    debug messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owiak
    -0.52
    AxisAlignment
    -0.52
    anko
    -0.51
     kese
    -0.50
     Parmi
    -0.50
     EXIST
    -0.50
     nargin
    -0.49
    Rohy
    -0.49
    tagon
    -0.49
     HasFactory
    -0.48
    POSITIVE LOGITS
     Initialized
    0.89
    tagHelperRunner
    0.81
     للاسماء
    0.78
    ArrowToggle
    0.72
     متعلقه
    0.71
     AspNetCore
    0.69
    <?
    0.66
     bezeichneter
    0.65
     الحره
    0.64
    DEBUG
    0.62
    Activations Density 0.019%

    No Known Activations