© 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. 8334
    Prev
    Next
    INDEX
    Explanations

    references to Outlook and technical support information about Microsoft products

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

    Programming- or help-related content

    np_acts-logits-general · gemini-2.0-flash

    resolving issues with links

    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
     Goy
    -0.51
    hastly
    -0.48
    Spoiler
    -0.47
     /\.(
    -0.47
    ydon
    -0.46
    substack
    -0.46
     Py
    -0.46
     endblock
    -0.46
    bukkit
    -0.45
     blast
    -0.45
    POSITIVE LOGITS
    ंदीखरीदारी
    0.76
    évaluateur
    0.71
    expandindo
    0.63
     '\\;'
    0.63
    eleste
    0.61
    parsedMessage
    0.61
     raiſ
    0.60
    elemField
    0.59
     dissol
    0.59
     troubleshooting
    0.59
    Activations Density 0.158%

    No Known Activations