© 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. 31437
    Prev
    Next
    INDEX
    Explanations

    escape characters and command line syntax related to scripting

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

    user inputs

    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
     Ooster
    -0.53
     OnTriggerEnter
    -0.52
     Roost
    -0.51
     moe
    -0.49
    AnchorTagHelper
    -0.49
    uque
    -0.49
    remont
    -0.48
     באתר
    -0.48
     Acti
    -0.48
     monster
    -0.48
    POSITIVE LOGITS
    setVerticalGroup
    0.52
     NSCoder
    0.45
    tagHelperRunner
    0.42
     capuz
    0.41
     creemos
    0.40
     metav
    0.40
    getMenuInflater
    0.39
     Vernunft
    0.38
    \{\\
    0.38
    SharedCtor
    0.37
    Activations Density 0.028%

    No Known Activations