© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 6956
    Prev
    Next
    INDEX
    Explanations

    function calls, particularly those related to array and collection operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Хьажоргаш
    -0.81
     pleaſure
    -0.79
     itſelf
    -0.77
    #
    -0.76
     myſelf
    -0.76
     ſche
    -0.70
    RenderAtEndOf
    -0.69
    ();)
    -0.66
     houſe
    -0.66
     Jefus
    -0.65
    POSITIVE LOGITS
    map
    1.35
     map
    0.80
    Map
    0.67
    MAP
    0.60
     Map
    0.59
    MLLoader
    0.56
    PageRoute
    0.56
    stdc
    0.56
     JpaRepository
    0.55
    Ser
    0.55
    Activations Density 0.034%

    No Known Activations