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. 97612
    Prev
    Next
    INDEX
    Explanations

    references to specific people, events, and technical terms related to health and programming

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

    european politicians and hurricanes

    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
     prêtres
    -0.36
    FormsModule
    -0.36
    Dor
    -0.34
     Dor
    -0.34
     olsun
    -0.34
     själva
    -0.34
     lenker
    -0.34
     Kodak
    -0.33
    Toggle
    -0.33
    lehem
    -0.33
    POSITIVE LOGITS
     Akufo
    1.87
    Addo
    1.37
    veni
    0.86
     Buhari
    0.65
     surla
    0.63
     AssemblyVersion
    0.61
     Obrador
    0.56
     Tinubu
    0.56
    himovic
    0.56
    WaitGroup
    0.55
    Activations Density 0.000%

    No Known Activations