© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6173
    Prev
    Next
    INDEX
    Explanations

    punctuation and general end-of-sentence markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]=="
    -0.44
     or
    -0.43
    uxxxx
    -0.42
     most
    -0.41
    DebuggerNonUser
    -0.40
     ?></
    -0.40
     ?>"
    -0.39
     Púb
    -0.38
     Kings
    -0.38
    EndInit
    -0.38
    POSITIVE LOGITS
    arakhand
    0.69
     Majefty
    0.63
     purpoſe
    0.62
    ſelf
    0.58
    enumii
    0.56
    볍
    0.56
     ſche
    0.55
     defaultstate
    0.53
    liothèque
    0.52
    ſelves
    0.52
    Activations Density 1.230%

    No Known Activations