© 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. 1594
    Prev
    Next
    INDEX
    Explanations

    complex relationships and dependencies between various variables or entities

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

    phrases describing measurement, comparison, or analysis using "in terms of".

    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
    而已
    -0.40
    neval
    -0.35
    prüche
    -0.35
    রণ
    -0.34
    latego
    -0.34
    楔
    -0.33
    ietic
    -0.32
    sätzlich
    -0.31
    enderror
    -0.31
    ായി
    -0.30
    POSITIVE LOGITS
     both
    3.36
    both
    3.05
     både
    2.70
     zarówno
    2.66
    Both
    2.63
     zowel
    2.56
     Both
    2.53
     sowohl
    2.50
     BOTH
    2.36
    BOTH
    2.30
    Activations Density 1.809%

    No Known Activations