© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11356
    Prev
    Next
    INDEX
    Explanations

    occurrences of conditional or preparatory phrases related to time and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    hyrchwyd
    -0.44
    MigrationBuilder
    -0.44
     zuge
    -0.43
    ivu
    -0.43
     ✭✭
    -0.41
     consequent
    -0.41
    Hentet
    -0.40
    GenerationType
    -0.40
     econômica
    -0.38
    kope
    -0.38
    POSITIVE LOGITS
     beforehand
    0.69
     before
    0.69
     Before
    0.68
     antes
    0.67
    Before
    0.65
    before
    0.65
     sebelum
    0.63
     înainte
    0.63
     BEFORE
    0.61
    Antes
    0.61
    Activations Density 0.180%

    No Known Activations