© 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. 2967
    Prev
    Next
    INDEX
    Explanations

    programming constructs and definitions related to generic types and stores in code

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

    TypeScript type definitions

    np_acts-logits-general · gemini-2.0-flash

    code keywords and symbols

    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
     da
    -0.47
     rep
    -0.44
     b
    -0.42
     A
    -0.42
    .
    -0.42
     Caribbean
    -0.42
    <eos>
    -0.40
    ,
    -0.40
    struct
    -0.40
    บ
    -0.40
    POSITIVE LOGITS
     Efq
    1.01
     ſtate
    0.95
     ftate
    0.90
     uſe
    0.89
     ſmall
    0.88
     raiſ
    0.86
     myſelf
    0.85
     Jefus
    0.85
     ſta
    0.83
     auroit
    0.82
    Activations Density 0.188%

    No Known Activations