© 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. 8245
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and online systems

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

    Follows the word "the"

    np_acts-logits-general · gemini-2.0-flash

    the consumption, unit, decomposition

    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
    berdayakan
    -0.52
     Unterscheidung
    -0.50
    tonode
    -0.48
     zijne
    -0.47
     halbe
    -0.47
     Einladung
    -0.45
     Grüsse
    -0.44
     Konsequ
    -0.44
    importanza
    -0.43
     Optionen
    -0.41
    POSITIVE LOGITS
    onViewCreated
    0.54
     concerned
    0.54
    ximity
    0.50
    basicConfig
    0.49
     ord
    0.47
     Италијани
    0.47
     Numerade
    0.46
     geng
    0.46
    AddTagHelper
    0.44
     posteriori
    0.44
    Activations Density 1.051%

    No Known Activations