© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 97229
    Prev
    Next
    INDEX
    Explanations

    references to options or choices in a system or programming context

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

    launching things

    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
     épais
    -0.31
     agujas
    -0.27
     équilibr
    -0.26
     extérieur
    -0.25
     refusé
    -0.24
     antemano
    -0.24
    😟
    -0.24
     éto
    -0.23
     jueves
    -0.23
     comédie
    -0.23
    POSITIVE LOGITS
    launch
    1.24
     launch
    1.21
     Launch
    1.19
    Launch
    1.13
     Launching
    1.12
     launching
    1.11
    Launching
    1.08
     LAUNCH
    1.07
     launchers
    0.99
    LAUNCH
    0.99
    Activations Density 0.004%

    No Known Activations