© 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. 13186
    Prev
    Next
    INDEX
    Explanations

    programming constructs and data handling in JSON

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

    JSON parsing and manipulation operations on nested object structures.

    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
    tinyos
    -0.53
    RectangleBorder
    -0.53
    XmlType
    -0.47
    ReusableCell
    -0.45
    JdbcTemplate
    -0.44
    ifflin
    -0.44
    MarshalTo
    -0.43
    ="#"><
    -0.43
    Datuak
    -0.42
    Hentet
    -0.42
    POSITIVE LOGITS
     obtenido
    0.41
     Bä
    0.41
    стоя
    0.40
    市镇
    0.39
    taña
    0.39
     становника
    0.38
     innamor
    0.38
    mybatisplus
    0.36
     Ba
    0.36
    MÁS
    0.36
    Activations Density 0.265%

    No Known Activations