© 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. 4475
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to scientific processes and methodologies

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

    Actions or processes

    np_acts-logits-general · gemini-2.0-flash

    actions, processes, or events

    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
     musiciens
    -0.35
     bailarina
    -0.35
     Stimme
    -0.32
    bietern
    -0.32
     constantemente
    -0.32
     abused
    -0.31
     compañero
    -0.31
     reformers
    -0.31
    digd
    -0.30
     integridad
    -0.30
    POSITIVE LOGITS
     sessions
    0.87
     session
    0.87
     experiments
    0.77
     negotiations
    0.76
     experiment
    0.75
     explorations
    0.74
     operations
    0.74
     exercises
    0.72
     photoshoot
    0.71
     ceremony
    0.70
    Activations Density 1.140%

    No Known Activations