© 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. 10294
    Prev
    Next
    INDEX
    Explanations

    the word "there" in various contexts

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

    "there" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    there is/are/was

    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
    DockStyle
    -0.66
    tagext
    -0.63
     TextAppearance
    -0.63
     useCallback
    -0.61
    BeginContext
    -0.58
    tableFuture
    -0.58
    AxisAlignment
    -0.57
    liani
    -0.57
    spesies
    -0.57
    SharedDtor
    -0.56
    POSITIVE LOGITS
    inafter
    0.72
    unto
    0.65
    peutic
    0.63
    tical
    0.59
     are
    0.58
    upon
    0.56
    fores
    0.54
    FORE
    0.54
    StoryboardSegue
    0.50
     befind
    0.50
    Activations Density 0.179%

    No Known Activations