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. 21-GEMMASCOPE-RES-16K
    6. 7403
    Prev
    Next
    INDEX
    Explanations

    statements regarding educational development and improvement strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ----------
    -0.61
    InitVars
    -0.60
    ---+
    -0.59
    PyExc
    -0.57
    Eksteraj
    -0.57
    ItemLayout
    -0.56
    Jereo
    -0.56
    contentLoaded
    -0.56
    ReferenceEquals
    -0.56
    ConstraintMaker
    -0.55
    POSITIVE LOGITS
    *
    1.44
     *
    1.03
    *}
    0.73
    *?
    0.72
    *
    
    0.70
    CppMethod
    0.69
    *;
    0.67
    ?*
    0.67
    *,
    0.66
     $*$
    0.66
    Activations Density 0.075%

    No Known Activations