© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4526
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, parentheses, brackets, or semicolons

    np_acts-logits-general · gemini-2.0-flash

    code ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.92
    `,
    -0.82
    "],
    -0.80
    ',
    -0.76
     ſind
    -0.74
     esternos
    -0.73
    enumii
    -0.73
    ="@+
    -0.71
    >",
    -0.71
     ujednoznacz
    -0.70
    POSITIVE LOGITS
    ↵↵
    0.52
    .
    0.48
    <eos>
    0.46
    </tr>
    0.38
     extranjera
    0.35
    ↵
    0.34
     vectorielle
    0.34
     destinées
    0.34
    ulihan
    0.34
    ↵↵↵
    0.33
    Activations Density 0.349%

    No Known Activations