© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7977
    Prev
    Next
    INDEX
    Explanations

    expressions of emphasis or intensity in describing qualities

    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
     fédé
    -0.57
     distanciation
    -0.55
     Económica
    -0.51
    principalColumn
    -0.51
     avoient
    -0.49
    RegressionTest
    -0.49
     geométrico
    -0.48
     mérit
    -0.46
     obé
    -0.46
     Wahrheit
    -0.45
    POSITIVE LOGITS
    wa
    0.69
    Navigation
    0.66
     especially
    0.66
     particularly
    0.63
    bas
    0.63
    IB
    0.63
     Navigation
    0.61
    especially
    0.60
    MB
    0.60
    wp
    0.60
    Activations Density 0.217%

    No Known Activations