© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 14092
    Prev
    Next
    INDEX
    Explanations

    HTML and Java related technical components, particularly those used in server configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ``
    -0.59
    <u>
    -0.54
    ``.
    -0.52
    stdafx
    -0.51
     ``
    -0.50
    য়ে
    -0.49
    InteropServices
    -0.48
    england
    -0.47
    ``,
    -0.47
    %@",
    -0.47
    POSITIVE LOGITS
    operator
    0.76
    argument
    0.72
    DECL
    0.69
    specifier
    0.66
    comment
    0.60
    TokenNameLPAREN
    0.57
     Chwiliwch
    0.56
    esModule
    0.56
     isNameExpr
    0.55
    XmlAccessType
    0.55
    Activations Density 0.105%

    No Known Activations