Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 14924
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss the passage of time and future outcomes

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

    uncertainty or lack of knowledge

    np_acts-logits-general · gemini-2.0-flash

    determine unknowns or discovery

    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
    aarrggbb
    -0.55
    INTER
    -0.49
     كومونز
    -0.48
    ต่อ
    -0.47
    ManagedBean
    -0.47
    IntoConstraints
    -0.46
    npmjs
    -0.45
     ThemeData
    -0.45
    ագրություններ
    -0.44
    таратура
    -0.44
    POSITIVE LOGITS
     unknow
    0.77
     guesses
    0.75
    kuuta
    0.73
     TESTS
    0.70
     speculating
    0.70
     scopri
    0.69
     unknowns
    0.68
     verification
    0.67
    guesses
    0.65
     tests
    0.64
    Activations Density 0.293%

    No Known Activations