© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5145
    Prev
    Next
    INDEX
    Explanations

    list and structure-related elements in code

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

    technical code snippets, particularly involving programming syntax like array indexing, method calls, and loop structures.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    UnknownFieldSet
    -0.54
     EconPapers
    -0.53
    ANTLR
    -0.52
    tagHelperRunner
    -0.51
     desmotivaciones
    -0.50
    WriteBarrier
    -0.50
    BASELINE
    -0.50
    :✨
    -0.49
    Déc
    -0.49
    ArrowToggle
    -0.47
    POSITIVE LOGITS
    PyTuple
    0.39
    ++]=
    0.31
    folg
    0.31
     ég
    0.30
    appendChild
    0.29
     tuyau
    0.29
     koos
    0.29
    ceğine
    0.27
    ientôt
    0.27
    itschrift
    0.26
    Activations Density 0.295%

    No Known Activations