© 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. 16-GEMMASCOPE-RES-16K
    11. 7771
    Prev
    Next
    INDEX
    Explanations

    statistical findings and discussions regarding significance in research studies

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

    Precedes "not" and indicates negation or uncertainty

    np_acts-logits-general · gemini-2.0-flash

    was not significant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.60
    LayoutParams
    -0.55
    }`).
    -0.50
    ValueGeneration
    -0.49
    adone
    -0.49
    ushi
    -0.48
    endphp
    -0.48
    genous
    -0.47
    원
    -0.47
    nze
    -0.46
    POSITIVE LOGITS
     &___
    0.68
    気の
    0.66
     placebo
    0.63
     mirage
    0.61
    LookAnd
    0.61
    GEBURTSDATUM
    0.60
     ErrIntOverflow
    0.58
    TabIndex
    0.58
     Wahrnehmung
    0.58
    fjspx
    0.58
    Activations Density 0.489%

    No Known Activations