© 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-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 5702
    Prev
    Next
    INDEX
    Explanations

    sentences that involve prerequisites or conditions for actions to take place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſche
    -0.48
    BigNumber
    -0.47
    acamata
    -0.46
    migrationBuilder
    -0.46
     omnia
    -0.46
    illo
    -0.44
     Shakspeare
    -0.44
    dostęp
    -0.43
     Punto
    -0.42
    ритори
    -0.42
    POSITIVE LOGITS
     terlebih
    1.71
     eerst
    1.53
     dulu
    1.52
    まずは
    1.41
     first
    1.40
     сначала
    1.34
    まず
    1.33
    先
    1.28
     zuerst
    1.26
     primero
    1.25
    Activations Density 0.407%

    No Known Activations