© 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. 31-GEMMASCOPE-RES-16K
    11. 3170
    Prev
    Next
    INDEX
    Explanations

    assertions and conditions related to specific cases or scenarios

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    conditional or hypothetical statements using "if...then" or "that is...the case" constructions.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     JpaRepository
    -0.54
    出版年
    -0.51
    stdc
    -0.42
    internalType
    -0.42
     referrerpolicy
    -0.41
     Hinge
    -0.40
    GORITH
    -0.40
    hoeddwyd
    -0.39
     Pig
    -0.39
     OnInit
    -0.38
    POSITIVE LOGITS
     case
    2.39
     caso
    1.92
     cases
    1.89
    case
    1.87
    Case
    1.66
     Case
    1.64
     kasus
    1.56
     CASE
    1.55
     casos
    1.50
     случае
    1.49
    Activations Density 0.666%

    No Known Activations