© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 78853
    Prev
    Next
    INDEX
    Explanations

    commands and invitations to take action, especially related to reading or continuing with content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    bootstrapcdn
    -1.34
     ſind
    -1.23
     queſta
    -1.21
     ſei
    -1.12
     $_(
    -1.09
    AddTagHelper
    -1.09
     Infórmanos
    -1.04
     ſeine
    -1.04
    niſſe
    -1.04
     صوتيه
    -1.02
    POSITIVE LOGITS
    .
    0.84
    ↵↵
    0.79
    <eos>
    0.66
    </tr>
    0.60
    ↵↵↵
    0.60
    }
    0.54
    !
    0.54
    ..
    0.52
     
    0.52
     */
    0.52
    Activations Density 0.011%

    No Known Activations