© 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. 7768
    Prev
    Next
    INDEX
    Explanations

    terms related to business strategy and market opportunities

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

    before specific verbs or uses of "is"

    np_acts-logits-general · gemini-2.0-flash

    growth opportunities, business model, leading science

    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
     texts
    -0.39
    WriteTagHelper
    -0.38
     ses
    -0.37
     setUp
    -0.37
     pep
    -0.36
     official
    -0.36
     OFFIC
    -0.36
    defaultProps
    -0.36
     peper
    -0.36
     fileList
    -0.36
    POSITIVE LOGITS
     differentiated
    0.63
    eaways
    0.58
    rzost
    0.56
     leveraging
    0.56
    Tikang
    0.54
    utenants
    0.54
     claridad
    0.54
    ніципалі
    0.54
     incumb
    0.53
     relever
    0.53
    Activations Density 0.426%

    No Known Activations