© 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. 20-GEMMASCOPE-RES-16K
    11. 329
    Prev
    Next
    INDEX
    Explanations

    numerical values and references to data structures or modules

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

    Tokens followed by a forward slash

    np_acts-logits-general · gemini-2.0-flash

    path segment or division

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngdoc
    -0.78
     nemlig
    -0.57
    .*")]
    -0.56
    Diweddarwch
    -0.55
     AttributeSet
    -0.55
     resourceCulture
    -0.55
    ">',
    -0.53
    __':
    -0.53
    FormTagHelper
    -0.50
     }}-
    -0.50
    POSITIVE LOGITS
    /
    1.88
     /
    1.52
    ／
    1.27
    '/
    1.18
     $/
    1.15
    "/
    1.13
    ./
    1.11
    ,/
    1.09
    /"
    1.09
    ()/
    1.08
    Activations Density 0.307%

    No Known Activations