© 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. 5-GEMMASCOPE-RES-16K
    11. 6241
    Prev
    Next
    INDEX
    Explanations

    question formats and specific query structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.73
     Eſ
    -0.66
     Jefus
    -0.65
     myſelf
    -0.65
     raiſ
    -0.64
     Anſ
    -0.64
    QMetaType
    -0.64
     Diſ
    -0.63
    shadowRadius
    -0.63
     Inſ
    -0.63
    POSITIVE LOGITS
    ⓧ
    0.66
    tvguidetime
    0.57
     bahkan
    0.53
    <bos>
    0.51
     incluso
    0.50
    <eos>
    0.50
    ม้
    0.49
     ?
    0.49
     combineReducers
    0.49
     even
    0.48
    Activations Density 0.375%

    No Known Activations