© 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 EvalsExportsAPI 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. 6799
    Prev
    Next
    INDEX
    Explanations

    terms related to the word "branch" and variations of it in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "branch" or words containing "branch" across diverse contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.44
     consultato
    -0.31
     Goodman
    -0.30
    ("="
    -0.30
     calcetines
    -0.30
    Karl
    -0.29
    pra
    -0.28
     Cedex
    -0.28
     żyw
    -0.28
     Qar
    -0.27
    POSITIVE LOGITS
     Branch
    0.95
     branch
    0.90
    Branch
    0.89
     BRANCH
    0.87
    branch
    0.86
     Branches
    0.85
     branches
    0.79
    Branches
    0.75
    branches
    0.75
    BRANCH
    0.73
    Activations Density 0.287%

    No Known Activations