© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 9813
    Prev
    Next
    INDEX
    Explanations

    instances of the term "missing" and its variations, indicating a focus on absent data or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Schild
    -0.52
    a
    -0.48
     k
    -0.47
    frey
    -0.45
    )
    -0.44
    ไร
    -0.44
     Rad
    -0.44
     Broad
    -0.43
     kor
    -0.43
    ner
    -0.43
    POSITIVE LOGITS
    endphp
    0.94
    utnik
    0.87
     defaultstate
    0.85
     betweenstory
    0.85
     paws
    0.85
     Arma
    0.84
    Fle
    0.84
     ſche
    0.82
    Arma
    0.80
     houſe
    0.80
    Activations Density 0.032%

    No Known Activations