© 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. 8197
    Prev
    Next
    INDEX
    Explanations

    function definitions and declarations in code

    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
     MTC
    -0.62
     MTS
    -0.57
     للاسماء
    -0.56
     propOrder
    -0.55
     pinulongan
    -0.55
    AndEndTag
    -0.53
    lictions
    -0.51
    chise
    -0.50
    Спасылкі
    -0.49
    nga
    -0.49
    POSITIVE LOGITS
    void
    2.09
     void
    1.84
    Void
    1.72
    VOID
    1.69
     Void
    1.58
     VOID
    1.53
     voids
    1.51
    layoutControl
    0.73
    SOUNDBITE
    0.73
    uol
    0.71
    Activations Density 0.035%

    No Known Activations