© 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. 3885
    Prev
    Next
    INDEX
    Explanations

    verbs indicating participation or action taken

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

    followed by "that"

    np_acts-logits-general · gemini-2.0-flash

    concluding a statement or result

    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
     and
    -0.53
    onViewCreated
    -0.42
     Fayette
    -0.41
     namelijk
    -0.41
    bote
    -0.40
     Camp
    -0.39
     Farn
    -0.39
     Flor
    -0.38
    liferay
    -0.38
     xr
    -0.37
    POSITIVE LOGITS
    +#+#
    0.85
     therefore
    0.68
     therefor
    0.65
    therefore
    0.59
     thereby
    0.59
     somit
    0.58
     sebagainya
    0.57
    Поэтому
    0.56
     withal
    0.56
     dermed
    0.54
    Activations Density 0.513%

    No Known Activations