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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 85872
    Prev
    Next
    INDEX
    Explanations

    elements of programming syntax related to lists and asynchronous tasks

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

    list of users or queries

    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
    saraba
    -0.45
    migrationBuilder
    -0.44
     sockaddr
    -0.43
    }))
    
    -0.42
    WebServlet
    -0.42
    MockBean
    -0.42
    Tembelea
    -0.41
    }}}{
    -0.41
     تضيفلها
    -0.40
    ="@+
    -0.40
    POSITIVE LOGITS
    UnusedPrivate
    0.44
     rendement
    0.43
     <>",
    0.41
    antwoorde
    0.38
    glEnd
    0.36
     recrutement
    0.35
     betale
    0.35
     fraude
    0.35
     rodzin
    0.34
    fficking
    0.34
    Activations Density 0.007%

    No Known Activations