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. 21-GEMMASCOPE-RES-16K
    6. 14339
    Prev
    Next
    INDEX
    Explanations

    occurrences of whitespace or formatted line breaks in text

    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
    Personendaten
    -0.73
    InjectAttribute
    -0.73
    بوابة
    -0.72
    Портал
    -0.64
    Portail
    -0.63
    bufio
    -0.61
     informée
    -0.60
    principalColumn
    -0.58
    PARATUS
    -0.58
     contextLoads
    -0.57
    POSITIVE LOGITS
    </blockquote>
    0.55
    User
    0.52
     služ
    0.46
     SPIE
    0.45
     InputDecoration
    0.44
    ConstraintMaker
    0.43
    MessageOf
    0.42
    ReactDOM
    0.42
    ApiProperty
    0.41
     rejoined
    0.41
    Activations Density 0.017%

    No Known Activations