© 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. 53434
    Prev
    Next
    INDEX
    Explanations

    temporal references in scientific contexts

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

    years and dates

    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
    RetentionPolicy
    -0.45
    الدراسه
    -0.40
     utafitiHapana
    -0.38
    IntoConstraints
    -0.37
    ChildScrollView
    -0.37
    odrome
    -0.37
     jamón
    -0.36
    setVerticalGroup
    -0.36
     שוליים
    -0.35
    amentlich
    -0.35
    POSITIVE LOGITS
    winter
    0.54
     winter
    0.52
     angelegt
    0.48
    RTGC
    0.46
     professionnel
    0.45
     photographe
    0.45
    twimg
    0.45
     observations
    0.44
     residente
    0.44
    volunteer
    0.44
    Activations Density 0.057%

    No Known Activations