© 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. 12-GEMMASCOPE-RES-16K
    11. 4104
    Prev
    Next
    INDEX
    Explanations

    elements related to code structure and programming imports

    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
    intios
    -0.50
    AndEndTag
    -0.48
     ब्रेकडाउन
    -0.47
     Infórmanos
    -0.46
     étoient
    -0.43
    tanleria
    -0.42
    Interviewer
    -0.42
    beiros
    -0.41
     asiática
    -0.41
     avoient
    -0.41
    POSITIVE LOGITS
    ConstraintMaker
    0.54
    __*/
    0.40
    )‏
    0.37
     fod
    0.37
     common
    0.36
     otomatig
    0.35
    <?>>
    0.35
     fo
    0.35
    NOPQRST
    0.35
     noqa
    0.34
    Activations Density 0.712%

    No Known Activations