Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 9999
    Prev
    Next
    INDEX
    Explanations

    references to roles, positions, and performances in the context of careers and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    continent
    -0.56
    ↹
    -0.53
    protoimpl
    -0.52
    wiesen
    -0.49
    thâu
    -0.49
    colnshire
    -0.46
     Continent
    -0.46
     continents
    -0.46
     continent
    -0.44
    Continent
    -0.44
    POSITIVE LOGITS
    Ligações
    0.49
     defaultstate
    0.48
    webElementXpaths
    0.47
     role
    0.46
     cameo
    0.41
     Tätigkeit
    0.41
     Auftritt
    0.41
    zeitige
    0.41
     nakalista
    0.40
    графія
    0.39
    Activations Density 0.749%

    No Known Activations