© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12904
    Prev
    Next
    INDEX
    Explanations

    information related to technical specifications and operational performance

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

    commas at the end of phrases that introduce a potential issue, limitation, or technical challenge.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    commas followed by numbers or numerical values in technical documentation.

    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
    __":
    -0.63
    __":
    -0.59
    __':
    -0.58
    LookAnd
    -0.57
    PerformLayout
    -0.56
    InjectAttribute
    -0.54
    libft
    -0.53
    tvguidetime
    -0.50
     InputDecoration
    -0.49
    __':
    -0.48
    POSITIVE LOGITS
     thereby
    1.67
     thus
    1.45
     allowing
    1.40
     waardoor
    1.32
     making
    1.30
     resulting
    1.30
     wodurch
    1.28
     causing
    1.26
     enabling
    1.25
    thus
    1.23
    Activations Density 1.617%

    No Known Activations