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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 92840
    Prev
    Next
    INDEX
    Explanations

    terms related to the permissions and conditions of software licensing

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

    software reproduction rights

    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
     surla
    -0.82
    :✨
    -0.63
    ❉
    -0.60
    Personendaten
    -0.60
    ########.
    -0.59
    AddHtmlAttribute
    -0.57
    -------------</
    -0.57
    rungsseite
    -0.57
     AssemblyTitle
    -0.56
    $_['
    -0.55
    POSITIVE LOGITS
     reproduction
    0.79
     Reproduction
    0.55
    Reproduction
    0.52
     reproducción
    0.49
     reproduce
    0.48
     reproduced
    0.41
     reprodução
    0.41
     reprodu
    0.41
     reproduces
    0.40
     reproducir
    0.40
    Activations Density 0.001%

    No Known Activations