Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 113397
    Prev
    Next
    INDEX
    Explanations

    references to community engagement and internal organizational initiatives

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

    champion, committee, and bee

    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
    Bioaccumulative
    -0.50
     dzie
    -0.43
     indústria
    -0.42
    colorado
    -0.41
     Rechts
    -0.41
     schlägt
    -0.41
     biznes
    -0.41
    łaty
    -0.40
     vermogen
    -0.40
    tidumbre
    -0.40
    POSITIVE LOGITS
    
    0.47
     препратки
    0.42
     Lingkungan
    0.41
    Xna
    0.40
     trainers
    0.40
    ModelBuilder
    0.39
    walks
    0.38
    autaire
    0.38
    barrow
    0.36
    initializeApp
    0.36
    Activations Density 0.188%

    No Known Activations