© 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
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 6746
    Prev
    Next
    INDEX
    Explanations

    terms related to processes, actions, and constructs in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    paramref
    -0.44
    IntoConstraints
    -0.44
    sidemargin
    -0.40
     ProtoMessage
    -0.38
    Personendaten
    -0.34
    Personensuche
    -0.33
     зе
    -0.32
    шое
    -0.31
    fjspx
    -0.31
     ali
    -0.30
    POSITIVE LOGITS
    ſelf
    0.59
     myſelf
    0.57
    ſelves
    0.55
     consultato
    0.53
    principalColumn
    0.52
     ſtate
    0.51
    scriptId
    0.50
     houſe
    0.49
     itſelf
    0.48
    drawString
    0.47
    Activations Density 0.663%

    No Known Activations