© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11018
    Prev
    Next
    INDEX
    Explanations

    key-value pairs in structured data formats

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

    Code snippets containing colons and quotation marks

    np_acts-logits-general · gemini-2.0-flash

    code, json, attributes

    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
    ;
    -0.67
    .
    -0.59
    NSURL
    -0.54
     –
    -0.54
     —
    -0.51
     in
    -0.50
     He
    -0.49
     NSError
    -0.49
    osgi
    -0.48
    dropna
    -0.48
    POSITIVE LOGITS
    OGND
    0.99
     Roskov
    0.99
    
    0.89
    ">:
    0.88
     CreateTagHelper
    0.88
    IsContent
    0.87
     }}"></
    0.87
    出版年
    0.84
    InjectAttribute
    0.80
    ✨:
    0.80
    Activations Density 0.244%

    No Known Activations