© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 4683
    Prev
    Next
    INDEX
    Explanations

    instances of the word "some" and its variations, indicating a focus on uncertainty or plurality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.73
    FunctionFlags
    -0.69
    orianCalendar
    -0.66
     onCreateView
    -0.65
    ValueStyle
    -0.61
     Audiodateien
    -0.59
    __*/
    -0.59
    LabelTagHelper
    -0.58
    ulent
    -0.57
     "..\..\..\
    -0.57
    POSITIVE LOGITS
    when
    0.73
    where
    0.73
    how
    0.73
    why
    0.72
    way
    0.72
    ways
    0.67
    wheres
    0.66
    both
    0.65
    wh
    0.64
    day
    0.64
    Activations Density 0.143%

    No Known Activations