© 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. 7738
    Prev
    Next
    INDEX
    Explanations

    occurrences of confrontational or violent actions

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

    following periods

    np_acts-logits-general · gemini-2.0-flash

    sequence word or phrase

    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
    aarrggbb
    -0.72
    IntoConstraints
    -0.68
     AssemblyCompany
    -0.66
     EconPapers
    -0.63
    endphp
    -0.62
     kasarigan
    -0.62
    UnusedPrivate
    -0.61
    UnknownFieldSet
    -0.60
     MainAxisSize
    -0.56
     prácti
    -0.56
    POSITIVE LOGITS
     After
    0.50
     thereupon
    0.49
     after
    0.48
     Using
    0.47
     soon
    0.47
     subsequently
    0.47
     using
    0.47
     Darauf
    0.47
     proceeded
    0.46
     vervolgens
    0.45
    Activations Density 0.572%

    No Known Activations