© 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. 28-GEMMASCOPE-RES-16K
    6. 4512
    Prev
    Next
    INDEX
    Explanations

    elements related to error codes and system signals

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

    The number 3 (often in a URL or with other numbers)

    np_acts-logits-general · gemini-2.0-flash

    numbers and ordinals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nthetic
    -0.51
    yarnpkg
    -0.48
    WebRequest
    -0.47
    nault
    -0.47
    createConnection
    -0.47
    tamo
    -0.45
     shovel
    -0.45
    rungsseite
    -0.44
     PARSER
    -0.44
    Inflater
    -0.44
    POSITIVE LOGITS
    3
    1.02
    rd
    0.93
    ßig
    0.66
     Infórmanos
    0.55
    ۳
    0.53
     kaarangay
    0.52
    rds
    0.51
    .³
    0.47
    3
    0.47
     treinta
    0.45
    Activations Density 0.992%

    No Known Activations