© 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. 24-GEMMASCOPE-RES-16K
    11. 11043
    Prev
    Next
    INDEX
    Explanations

    trivial punctuation marks and formatting elements in text

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

    Code, layouts, or punctuation

    np_acts-logits-general · gemini-2.0-flash

    IRI, 6, REF

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     here
    -0.60
     del
    -0.56
     dei
    -0.56
     e
    -0.52
     #
    -0.51
     <
    -0.50
     na
    -0.50
     let
    -0.50
     Reis
    -0.48
    "#
    -0.48
    POSITIVE LOGITS
    styleType
    0.90
    uxxxx
    0.85
     invokingState
    0.85
    principalColumn
    0.81
    Autoritní
    0.78
    Location
    0.78
    Jeografia
    0.77
    ыгана
    0.74
     CreateTagHelper
    0.74
    ⓧ
    0.73
    Activations Density 0.007%

    No Known Activations