© 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. 14277
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "initial" and its variations in context

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

    Following "initial"

    np_acts-logits-general · gemini-2.0-flash

    initial state or problem

    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
    fiable
    -0.54
    InjectAttribute
    -0.53
     brazo
    -0.52
    kuuta
    -0.51
    chluss
    -0.50
    processData
    -0.48
    LEncoder
    -0.47
     foly
    -0.47
     cortos
    -0.46
    тельством
    -0.45
    POSITIVE LOGITS
    LabelTagHelper
    0.99
    contentLoaded
    0.77
    RenderAtEndOf
    0.75
     iſt
    0.75
     Basili
    0.74
     تضيفلها
    0.73
     Efq
    0.73
     faſt
    0.72
     stages
    0.72
     facie
    0.71
    Activations Density 0.143%

    No Known Activations