© 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. 4-GEMMASCOPE-RES-16K
    11. 1763
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific identifiers related to software and coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getItemId
    -1.01
    InputModule
    -0.91
    fillType
    -0.89
    Personendaten
    -0.83
    omla
    -0.82
    VIAF
    -0.79
    CORBA
    -0.78
    setContentView
    -0.78
    LayoutInflater
    -0.78
    ValueStyle
    -0.77
    POSITIVE LOGITS
    ac
    0.95
     Rac
    0.93
    lic
    0.93
    cic
    0.92
    lec
    0.92
    poc
    0.90
    tac
    0.89
     Buc
    0.87
    alec
    0.87
    Xc
    0.85
    Activations Density 9.941%

    No Known Activations