© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3276
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation

    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
     invokingState
    -0.59
     nahilalakip
    -0.45
    transQ
    -0.45
    帖最后由
    -0.45
    )_/¯
    -0.42
    ophysical
    -0.42
     astore
    -0.38
    }*/
    -0.34
    engkapnya
    -0.33
     дописавши
    -0.33
    POSITIVE LOGITS
    addPreferredGap
    0.48
    tinyos
    0.43
    (:,:,
    0.41
    setLayoutManager
    0.40
    ConstraintSet
    0.40
    addContainerGap
    0.39
     opérateur
    0.39
     uVar
    0.39
     JScrollPane
    0.38
     pes
    0.38
    Activations Density 1.319%

    No Known Activations