© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 10888
    Prev
    Next
    INDEX
    Explanations

    references to data, evidence, or reports used in research or analysis

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

    phrases that cite sources or evidence to support claims.

    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
     ब्रेकडाउन
    -0.54
    RenderAtEndOf
    -0.49
    Подробнее
    -0.41
     tém
    -0.40
    IntoConstraints
    -0.39
     Topics
    -0.39
    ="@+
    -0.38
    DrawerToggle
    -0.38
    Procedures
    -0.38
    featureID
    -0.38
    POSITIVE LOGITS
     interviews
    1.00
     observations
    0.97
     observation
    0.82
     anecdotal
    0.81
     experience
    0.79
     literature
    0.76
     conversations
    0.75
     testimonies
    0.75
     entrevistas
    0.75
     historical
    0.74
    Activations Density 0.969%

    No Known Activations