© 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. 3-GEMMASCOPE-RES-16K
    11. 8905
    Prev
    Next
    INDEX
    Explanations

    terms related to observations or results in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    انتهای
    -0.58
     transfieras
    -0.51
    󠁣
    -0.47
    INSEE
    -0.47
    orari
    -0.44
    principalTable
    -0.43
    ">//
    -0.43
    GTCX
    -0.42
    featureID
    -0.40
    endfor
    -0.40
    POSITIVE LOGITS
     observed
    1.84
     discovered
    1.72
     noticed
    1.71
     detected
    1.68
    observed
    1.59
     Observed
    1.54
     spotted
    1.49
    discovered
    1.39
    Observed
    1.38
     identified
    1.37
    Activations Density 0.237%

    No Known Activations