© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 14109
    Prev
    Next
    INDEX
    Explanations

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

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

    "Some" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    some followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WireFormat
    -0.59
    UnusedPrivate
    -0.57
    ElementException
    -0.56
    er
    -0.54
     intptr
    -0.53
    se
    -0.53
    LookAnd
    -0.53
     onCancelled
    -0.52
    DataPropertyName
    -0.52
     VizieR
    -0.51
    POSITIVE LOGITS
    things
    0.93
     sort
    0.87
     SOM
    0.73
    bodies
    0.72
    wheres
    0.71
    bod
    0.70
     degree
    0.69
     serious
    0.68
     very
    0.68
     cuantos
    0.67
    Activations Density 0.159%

    No Known Activations