© 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. 3565
    Prev
    Next
    INDEX
    Explanations

    patterns and structures in data representation

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

    numerical values and sequences in structured data.

    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
    IonicModule
    -0.42
     față
    -0.38
     antemano
    -0.38
     caracteriza
    -0.37
     esponja
    -0.36
     capucha
    -0.36
    antado
    -0.36
     characterize
    -0.36
    Glej
    -0.35
     Charakter
    -0.35
    POSITIVE LOGITS
     twenty
    0.54
     Twenty
    0.52
    WireFormatLite
    0.52
     minOccurs
    0.50
     canst
    0.48
    msgTypes
    0.48
     Chwiliwch
    0.47
    withOpacity
    0.45
    dafx
    0.44
    帖最后由
    0.44
    Activations Density 0.427%

    No Known Activations