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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 10753
    Prev
    Next
    INDEX
    Explanations

    code-related terms and function definitions in programming contexts

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

    Code snippets related to Redux reducers

    np_acts-logits-general · gemini-2.0-flash

    actions and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esterno
    -0.46
    Amicalement
    -0.46
    zel
    -0.44
    guera
    -0.43
    tempts
    -0.43
     consentimiento
    -0.42
     .=
    -0.42
    tagHelper
    -0.42
    posits
    -0.41
    LabelTagHelper
    -0.41
    POSITIVE LOGITS
     reducer
    0.91
    redux
    0.88
     Reducer
    0.88
     reducers
    0.85
     Redux
    0.82
    Reducer
    0.82
    dispatch
    0.82
     REDUC
    0.80
     rootReducer
    0.79
    reducers
    0.76
    Activations Density 0.133%

    No Known Activations