© 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 - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2898
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and functions in a technical context

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

    Follows punctuation or structural elements

    np_acts-logits-general · gemini-2.0-flash

    numerical data following 7

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -1.08
     كومونز
    -1.07
     tartalomajánló
    -0.96
     مرئيه
    -0.93
     surla
    -0.88
    Datuak
    -0.85
    脚注の使い方
    -0.84
    ReusableCell
    -0.84
    StructEnd
    -0.84
    jooq
    -0.83
    POSITIVE LOGITS
    ↵↵
    0.65
    ↵
    0.62
    </h2>
    0.58
    </strong>
    0.57
    <strong>
    0.57
    </em>
    0.54
    ↵↵↵
    0.53
    <h4>
    0.50
    .
    0.49
    ActivityCompat
    0.48
    Activations Density 0.710%

    No Known Activations