© 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. 123245
    Prev
    Next
    INDEX
    Explanations

    structured data elements, particularly those related to software or digital project metadata

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

    JSON keys and values

    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
    Personendaten
    -0.85
    InjectAttribute
    -0.79
     betweenstory
    -0.75
    MessageTagHelper
    -0.70
    pholes
    -0.67
    OGND
    -0.66
    UnusedPrivate
    -0.66
    PerformLayout
    -0.65
    AndEndTag
    -0.63
    GEBURTS
    -0.61
    POSITIVE LOGITS
    .*")]
    0.33
     tentu
    0.31
     EconPapers
    0.30
     AssemblyCulture
    0.30
     distribution
    0.30
    配
    0.28
     distribuzione
    0.28
     Distribution
    0.28
     Gro
    0.28
    ütü
    0.27
    Activations Density 0.014%

    No Known Activations