© 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. 12-GEMMASCOPE-RES-16K
    6. 5905
    Prev
    Next
    INDEX
    Explanations

    terms related to privacy policies and practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.87
    GEBURTSDATUM
    -0.72
     ब्रेकडाउन
    -0.71
    PyExc
    -0.65
    UseVisualStyle
    -0.57
    tagHelperRunner
    -0.56
     defaultstate
    -0.52
     autorytatywna
    -0.52
    RectangleBorder
    -0.50
    AddTagHelper
    -0.50
    POSITIVE LOGITS
    UserScript
    0.36
    enschaft
    0.35
    itinéraire
    0.35
    urate
    0.34
    nteral
    0.33
     generally
    0.33
    gelijke
    0.33
    핍
    0.32
    cyj
    0.32
    mphony
    0.32
    Activations Density 0.312%

    No Known Activations