© 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. 7-GEMMASCOPE-RES-16K
    6. 15271
    Prev
    Next
    INDEX
    Explanations

    phrases related to the impact of various factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    étoit
    -0.42
     vendedores
    -0.39
     voorwaarden
    -0.36
     dochter
    -0.35
     mueble
    -0.35
     ouder
    -0.35
     mówią
    -0.34
     eletrônico
    -0.34
     regole
    -0.34
     vectorielles
    -0.34
    POSITIVE LOGITS
     impact
    2.95
     Impact
    2.86
    Impact
    2.81
    impact
    2.78
     IMPACT
    2.56
    IMPACT
    2.41
     impacts
    2.34
     Impacts
    2.23
     impacto
    2.17
     impacting
    2.14
    Activations Density 0.062%

    No Known Activations