© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1222
    Prev
    Next
    INDEX
    Explanations

    specific patterns of punctuation and punctuation-related expressions

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

    Math formulas or expressions

    np_acts-logits-general · gemini-2.0-flash

    dial perforating

    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
     vectorielles
    -0.71
    󠁢
    -0.69
     peines
    -0.63
    stretchr
    -0.62
    igshid
    -0.61
     esportivo
    -0.61
    \{\\
    -0.61
     abstrato
    -0.59
     vermelhas
    -0.58
    Референце
    -0.57
    POSITIVE LOGITS
    <bos>
    1.27
     tartalomajánló
    0.97
    LookAnd
    0.87
    tagHelperRunner
    0.81
    memoized
    0.73
    GEBURTSDATUM
    0.72
    تقاوى
    0.64
    PYX
    0.63
    Jeografia
    0.62
     виправивши
    0.60
    Activations Density 1.296%

    No Known Activations