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. 17-GEMMASCOPE-RES-16K
    6. 11012
    Prev
    Next
    INDEX
    Explanations

    expressions of frequency or repetition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intptr
    -0.81
    Coordonnées
    -0.63
     NgModule
    -0.62
     שוליים
    -0.59
    MigrationBuilder
    -0.59
    onOptions
    -0.56
    ConfigureAwait
    -0.56
     tồn
    -0.52
     ThemeData
    -0.51
    endregion
    -0.51
    POSITIVE LOGITS
    oubted
    0.61
     nữa
    0.59
    Personendaten
    0.57
     layui
    0.56
    bidden
    0.55
    RenderAtEndOf
    0.55
    قه
    0.52
    artney
    0.52
    esgue
    0.51
    imper
    0.51
    Activations Density 0.185%

    No Known Activations