© 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. 38-GEMMASCOPE-RES-16K
    6. 8184
    Prev
    Next
    INDEX
    Explanations

    words related to notable actions and roles within a community or society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.68
    Искәрмәләр
    -0.65
     miniaturka
    -0.65
     queſta
    -0.61
    #+#
    -0.60
    writeFieldEnd
    -0.59
     дописавши
    -0.58
    ########.
    -0.56
     lenker
    -0.55
     $_(
    -0.55
    POSITIVE LOGITS
     jointly
    0.62
     successively
    0.54
     respectively
    0.51
     variously
    0.49
     famously
    0.47
     recently
    0.46
     alternately
    0.44
    recently
    0.43
     encantan
    0.43
     posthum
    0.42
    Activations Density 1.059%

    No Known Activations