© 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. 0-GEMMASCOPE-RES-16K
    11. 3063
    Prev
    Next
    INDEX
    Explanations

    terms related to reduction or minimization in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     krav
    -0.44
    estens
    -0.43
    faser
    -0.41
    wa
    -0.41
    za
    -0.40
    <strong>
    -0.40
    ATOS
    -0.40
     Bes
    -0.40
    uten
    -0.39
    als
    -0.39
    POSITIVE LOGITS
     reduce
    1.00
     Reduce
    0.98
    Reduce
    0.97
     reduction
    0.96
     réduit
    0.94
     reduced
    0.94
     Reduction
    0.93
    reduced
    0.90
    reduction
    0.90
    Reduction
    0.90
    Activations Density 0.270%

    No Known Activations