© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 13995
    Prev
    Next
    INDEX
    Explanations

    terms related to legal conduct and violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    behavior and its consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     profit
    -0.33
     contextLoads
    -0.32
     matri
    -0.31
     Vor
    -0.30
     mati
    -0.28
     conveyance
    -0.28
     Christo
    -0.28
     Comple
    -0.27
     substan
    -0.27
     пун
    -0.26
    POSITIVE LOGITS
     behaviour
    1.10
     behavior
    1.09
    behavior
    1.05
     Behaviour
    1.01
     comportements
    1.00
     behaviours
    0.99
     Behavior
    0.97
     comportamento
    0.97
     behaviors
    0.97
     comportamiento
    0.97
    Activations Density 0.166%

    No Known Activations