© 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. 18-GEMMASCOPE-RES-16K
    6. 3392
    Prev
    Next
    INDEX
    Explanations

    expressions related to the existence or state of objects and actions

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

    "is" or "are" as a verb

    np_acts-logits-general · gemini-2.0-flash

    is/are followed by participle or descriptor

    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
     infatti
    -0.76
    tagHelperRunner
    -0.66
    djangoproject
    -0.65
    DoubleQuotes
    -0.65
     olyan
    -0.64
     inoltre
    -0.62
    AnchorTagHelper
    -0.60
     totiž
    -0.60
     natomiast
    -0.59
     surla
    -0.59
    POSITIVE LOGITS
     hopefully
    0.69
     leaſt
    0.68
    qtt
    0.63
    ]--;
    0.63
    tonsoft
    0.63
     otherwise
    0.63
    āya
    0.60
     endregion
    0.60
    NUMX
    0.59
     appunto
    0.59
    Activations Density 0.501%

    No Known Activations