© 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. 8281
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure

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

    Code, brackets, or unusual characters

    np_acts-logits-general · gemini-2.0-flash

    names or numbers followed by punctuation

    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
    Espèce
    -0.64
    addPreferredGap
    -0.63
    offsetof
    -0.63
    #+#
    -0.58
     Vikipedi
    -0.57
    LElement
    -0.55
    bulin
    -0.54
     متعلقه
    -0.54
    новништво
    -0.53
    reactstrap
    -0.52
    POSITIVE LOGITS
     /\.(
    0.58
     ne
    0.52
    !("{
    0.51
     विश्वसनीयता
    0.49
    ادث
    0.49
    fige
    0.49
    queros
    0.47
     незавершена
    0.46
    otto
    0.46
    <()>
    0.46
    Activations Density 0.236%

    No Known Activations