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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 57167
    Prev
    Next
    INDEX
    Explanations

    dashes or hyphens used in various contexts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trom
    -0.52
    Other
    -0.49
     supri
    -0.47
     itſelf
    -0.47
     Probleme
    -0.47
    くれました
    -0.47
     anla
    -0.46
     puol
    -0.46
    others
    -0.46
    ement
    -0.46
    POSITIVE LOGITS
     ujednoznacz
    1.02
    endphp
    0.97
    ValueStyle
    0.96
    __':
    0.87
    awtextra
    0.83
     nakalista
    0.82
    — 
    0.82
    __":
    0.79
     незавершена
    0.79
    }$​
    0.79
    Activations Density 0.009%

    No Known Activations