© 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. 34-GEMMASCOPE-RES-16K
    11. 7486
    Prev
    Next
    INDEX
    Explanations

    specific phrases that indicate reasoning or justification for actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -0.60
    expandindo
    -0.53
     Infórmanos
    -0.52
     виправивши
    -0.51
     dafür
    -0.48
    endorong
    -0.46
    basicConfig
    -0.46
    RenderAtEndOf
    -0.44
    adakan
    -0.44
     elkaar
    -0.43
    POSITIVE LOGITS
     purposes
    2.16
    purposes
    1.73
     sake
    1.58
     Purposes
    1.58
     purpose
    1.45
     Zwecke
    1.23
    purpose
    1.16
     reasons
    1.09
    Purpose
    1.05
     Purpose
    1.05
    Activations Density 0.918%

    No Known Activations