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. 4-GEMMASCOPE-RES-16K
    6. 738
    Prev
    Next
    INDEX
    Explanations

    instances of the keyword "abstract" as well as related programming structure identifiers

    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
    enumi
    -0.57
    +:+
    -0.54
     spie
    -0.48
    SafeAreaView
    -0.47
    pe
    -0.45
    WC
    -0.44
    das
    -0.44
     posti
    -0.43
    step
    -0.43
     seeded
    -0.43
    POSITIVE LOGITS
    RenderAtEndOf
    0.74
     myſelf
    0.70
    JspWriter
    0.70
     tartalomajánló
    0.68
     Efq
    0.66
    IntoConstraints
    0.65
     propOrder
    0.61
    ynchronously
    0.61
     كومونز
    0.60
     purpoſe
    0.60
    Activations Density 0.372%

    No Known Activations