© 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. 20-GEMMASCOPE-RES-131K
    6. 113033
    Prev
    Next
    INDEX
    Explanations

    terms related to database connections and operations

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

    database connection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.60
    fortawesome
    -0.53
     noDo
    -0.48
     protoimpl
    -0.48
     հղումներ
    -0.46
     PhpStorm
    -0.46
    دانشنامهٔ
    -0.46
     endwhile
    -0.46
     Mait
    -0.46
     MainAxisSize
    -0.45
    POSITIVE LOGITS
     SqlConnection
    0.53
     scaricare
    0.44
     ivelany
    0.41
     Connors
    0.38
     oplossing
    0.38
     organisatie
    0.38
     franquicia
    0.38
     tarko
    0.37
     herida
    0.37
    Connection
    0.37
    Activations Density 0.001%

    No Known Activations