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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4086
    Prev
    Next
    INDEX
    Explanations

    references to community activities and participation

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

    activities or challenges

    np_acts-logits-general · gemini-2.0-flash

    'bob for a job' / 'Find' / 'healthy'

    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
     ويكيميديا
    -0.38
     ligiloj
    -0.34
     deuil
    -0.33
    -------------</
    -0.32
     bý
    -0.31
     légal
    -0.30
    🔕
    -0.29
     soie
    -0.27
     akses
    -0.27
     kteří
    -0.27
    POSITIVE LOGITS
     quiz
    0.84
     scavenger
    0.78
    quiz
    0.74
     prank
    0.72
     Quiz
    0.71
     questionnaire
    0.70
     quizzes
    0.68
     QUIZ
    0.67
    Quiz
    0.67
     Questionnaire
    0.65
    Activations Density 0.193%

    No Known Activations