© 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14267
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical values or calculations

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

    Collect and What

    np_acts-logits-general · gemini-2.0-flash

    collect and what is

    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
     beſte
    -0.62
     ſtate
    -0.61
     ſta
    -0.61
     ſch
    -0.59
     CanadaChoose
    -0.58
     erſt
    -0.57
    TokenNameDOT
    -0.57
     ſich
    -0.56
    ſicht
    -0.56
     ſever
    -0.55
    POSITIVE LOGITS
    Personendaten
    0.47
    Autoritní
    0.46
    parsedMessage
    0.45
    RuleContext
    0.39
    InjectAttribute
    0.37
    offsetof
    0.35
    IUrlHelper
    0.35
    UnusedPrivate
    0.35
     zuk
    0.34
    uxxxx
    0.34
    Activations Density 0.128%

    No Known Activations