Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 474
    Prev
    Next
    INDEX
    Explanations

    references to music and pop culture

    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
     resourceCulture
    -0.75
    GEBURTSDATUM
    -0.75
     CreateTagHelper
    -0.64
    tagext
    -0.61
     protoimpl
    -0.61
     edelstahl
    -0.61
    MigrationBuilder
    -0.59
    省市镇
    -0.59
    исленность
    -0.58
     centuries
    -0.57
    POSITIVE LOGITS
     StatelessWidget
    0.65
    SequentialGroup
    0.56
    feinander
    0.55
    enumii
    0.52
     StatefulWidget
    0.52
    SizeF
    0.48
     <-
    0.48
    quiao
    0.47
    hyo
    0.46
     HttpHeaders
    0.46
    Activations Density 0.223%

    No Known Activations