© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 449
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and symbols commonly found in programming or markup languages

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

    Code snippets or file paths

    np_acts-logits-general · gemini-2.0-flash

    technical terms and code snippets

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     AssemblyCulture
    -0.90
     betweenstory
    -0.80
     kasarigan
    -0.79
     CURIAM
    -0.73
    oredCriteria
    -0.72
     MainAxisSize
    -0.69
     Infórmanos
    -0.68
    migrationBuilder
    -0.67
     queſta
    -0.67
    GOTREF
    -0.66
    POSITIVE LOGITS
    nasium
    0.30
    之
    0.28
     Einf
    0.28
     про
    0.28
     zvuky
    0.25
     is
    0.25
    væ
    0.25
    Access
    0.25
    Class
    0.24
     tayang
    0.24
    Activations Density 0.150%

    No Known Activations