© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 16310
    Prev
    Next
    INDEX
    Explanations

    references to APIs and related resources

    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
    annica
    -0.90
     lenker
    -0.82
     <<<<<<<<<<<<<<
    -0.75
    Cyfeiriadau
    -0.72
    principalColumn
    -0.72
    GEBURTSDATUM
    -0.70
    
    -0.70
    Tembelea
    -0.68
    ⓧ
    -0.67
    NewUrlParser
    -0.66
    POSITIVE LOGITS
    memoized
    0.50
    this
    0.46
     egli
    0.46
     avven
    0.43
    ’
    0.43
    fn
    0.43
    ym
    0.39
    box
    0.39
    fluor
    0.39
    </strong>
    0.38
    Activations Density 0.292%

    No Known Activations