© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8950
    Prev
    Next
    INDEX
    Explanations

    references to previously stated points or claims in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h1>
    -0.51
    等
    -0.44
     Mad
    -0.39
    ظه
    -0.39
     comporta
    -0.39
     sabe
    -0.38
    <eos>
    -0.38
    수
    -0.38
     «
    -0.37
    この
    -0.37
    POSITIVE LOGITS
    évaluateur
    0.91
    featureID
    0.90
    uxxxx
    0.85
     صوتيه
    0.84
    RegressionTest
    0.82
    CloseOperation
    0.79
    Personendaten
    0.79
    GraphicsUnit
    0.79
    :✨
    0.78
    ✨:
    0.75
    Activations Density 0.099%

    No Known Activations