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. 21396
    Prev
    Next
    INDEX
    Explanations

    terms related to biological systems and their functions

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

    technical components and their functions

    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
    AndEndTag
    -0.72
     вікісторінку
    -0.55
    itename
    -0.54
    IntoConstraints
    -0.52
     Exacts
    -0.49
    HideFlags
    -0.48
    enablog
    -0.46
    WireFormatLite
    -0.45
    attutto
    -0.44
    évaluateur
    -0.44
    POSITIVE LOGITS
    ագրություններ
    0.34
     many
    0.33
     often
    0.32
    }}^
    0.32
     OFDb
    0.32
     quite
    0.32
     muchos
    0.31
     depending
    0.30
     Cancelar
    0.30
     Gericht
    0.30
    Activations Density 0.180%

    No Known Activations