© 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. 1470
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and expressions related to matrices and their properties

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

    Mathematical notation/formula

    np_acts-logits-general · gemini-2.0-flash

    mathematical quantity relationships

    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
     GenerationType
    -0.48
    +#+
    -0.45
     calyx
    -0.44
    MLLoader
    -0.43
    НИК
    -0.42
    naphthal
    -0.40
    DeleteBehavior
    -0.40
    approved
    -0.40
     Cyclone
    -0.38
     galvan
    -0.37
    POSITIVE LOGITS
     незавершена
    0.61
     Verhältnisse
    0.55
    AndEndTag
    0.53
     Chwiliwch
    0.51
    tagHelperRunner
    0.50
    Tikang
    0.49
    Atentamente
    0.48
     quelcon
    0.48
     quelconque
    0.48
     selve
    0.47
    Activations Density 3.130%

    No Known Activations