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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 564
    Prev
    Next
    INDEX
    Explanations

    programming or script-related terms specifically involving installation parameters

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

    hexadecimal and numeric bit/architecture specifications in technical configuration files.

    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
     Trock
    -0.37
    뻐
    -0.36
    +#+#
    -0.34
    檔
    -0.33
     InputDecoration
    -0.33
    cdnjs
    -0.33
    head
    -0.33
    Dutch
    -0.31
    Blue
    -0.31
     bounce
    -0.30
    POSITIVE LOGITS
    architecture
    0.78
     architecture
    0.73
     architectures
    0.72
     ARCHITECTURE
    0.68
     bit
    0.66
     arquitectura
    0.66
     Architecture
    0.66
    architect
    0.65
     architects
    0.63
    ARCHITECTURE
    0.63
    Activations Density 0.635%

    No Known Activations