© 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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10362
    Prev
    Next
    INDEX
    Explanations

    terms related to biochemical interactions and processes, specifically those involving lipids and proteins

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

    Lipid membrane interactions, especially with vesicles

    np_acts-logits-general · gemini-2.0-flash

    lipid vesicles interacting

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     autorytatywna
    -0.50
    writerow
    -0.44
     Wurzeln
    -0.42
    Зміст
    -0.42
     bakgrund
    -0.39
     Pary
    -0.39
     vägen
    -0.39
     vectoriales
    -0.38
     Erwartungen
    -0.38
     reflexão
    -0.37
    POSITIVE LOGITS
     BoxFit
    0.49
    providedIn
    0.46
    PRNewswire
    0.45
     Numerade
    0.44
    LayoutPanel
    0.42
     generously
    0.42
    Портали
    0.41
     hab
    0.41
    LITERAL
    0.41
     Wikimedijinoj
    0.40
    Activations Density 0.993%

    No Known Activations