© 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. 2562
    Prev
    Next
    INDEX
    Explanations

    information related to code generation and permissions within programming contexts

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

    Code or version numbers

    np_acts-logits-general · gemini-2.0-flash

    code generation comments

    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
     insuffisamment
    -0.73
    glPopMatrix
    -0.71
    liferay
    -0.67
    XDECREF
    -0.58
     useAppContext
    -0.58
     AssemblyCulture
    -0.58
     tartalomajánló
    -0.57
     OMITBAD
    -0.56
     henvisninger
    -0.54
    endforeach
    -0.54
    POSITIVE LOGITS
    CodeAttribute
    1.68
    CodeDom
    0.66
    httphttps
    0.65
    TypedDataSet
    0.63
    tvguidetime
    0.57
    ADELPHIA
    0.55
     Roskov
    0.52
    --]
    0.51
     incomplète
    0.49
     ExecuteAsync
    0.48
    Activations Density 0.032%

    No Known Activations