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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15046
    Prev
    Next
    INDEX
    Explanations

    references to specific entities and their relationships

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

    Excluding or negating certain conditions

    np_acts-logits-general · gemini-2.0-flash

    excluding

    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
     mérite
    -0.30
    Personendaten
    -0.30
    AccessorTable
    -0.29
     Disponible
    -0.29
    的呢
    -0.28
     betrieben
    -0.28
    Disponible
    -0.28
     []:
    -0.27
    来说
    -0.27
    出版年
    -0.27
    POSITIVE LOGITS
    :✨
    0.72
    MigrationBuilder
    0.67
    setVerticalGroup
    0.58
     linkovi
    0.57
     betweenstory
    0.56
    EndGlobalSection
    0.54
     exclusions
    0.53
     Exclude
    0.53
     exclude
    0.52
    copg
    0.52
    Activations Density 0.522%

    No Known Activations