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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5592
    Prev
    Next
    INDEX
    Explanations

    patterns and structures in programming syntax or code formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     myſelf
    -0.90
     juſ
    -0.88
     ſtate
    -0.83
     purpoſe
    -0.79
     ſtre
    -0.77
     faſt
    -0.77
     itſelf
    -0.77
     ſon
    -0.77
     pleaſure
    -0.76
     ſever
    -0.75
    POSITIVE LOGITS
    .
    0.71
    ']").
    0.67
    */].
    0.65
    <bos>
    0.61
    ]').
    0.60
    ->
    0.59
     ($.
    0.56
     .
    0.56
    ("$.
    0.55
    }$.
    0.55
    Activations Density 0.468%

    No Known Activations