© 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. 119753
    Prev
    Next
    INDEX
    Explanations

    variations of the term "forward" and references to motion

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

    time progression or media

    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
     CreateTagHelper
    -0.35
     taxon
    -0.34
    EXC
    -0.34
     sûre
    -0.32
    ScopeManager
    -0.32
    egg
    -0.32
    name
    -0.31
    UIColor
    -0.30
     HTTP
    -0.28
     Forms
    -0.28
    POSITIVE LOGITS
     rewind
    0.79
    SequentialGroup
    0.66
    addGap
    0.65
    SOUNDBITE
    0.63
     WaitForSeconds
    0.63
    Flashback
    0.61
    BufferException
    0.61
     zooming
    0.59
    addPreferredGap
    0.59
     surla
    0.59
    Activations Density 0.005%

    No Known Activations