© 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. 28-GEMMASCOPE-RES-16K
    11. 7681
    Prev
    Next
    INDEX
    Explanations

    references to literary collections and their attributes

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

    Describing creative works (book, film, tale)

    np_acts-logits-general · gemini-2.0-flash

    evaluating media or narratives

    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
    ParameterName
    -0.36
     ioe
    -0.35
     Added
    -0.35
     inter
    -0.34
     esternos
    -0.34
     oko
    -0.34
     occaf
    -0.34
     G
    -0.33
     working
    -0.33
     Rib
    -0.33
    POSITIVE LOGITS
     worthy
    0.64
     that
    0.60
     '\\;'
    0.60
     nobody
    0.58
     deserving
    0.57
     ninguém
    0.54
     deemed
    0.52
    +#+#
    0.52
    nobody
    0.52
     AssemblyCulture
    0.52
    Activations Density 0.412%

    No Known Activations