Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 8985
    Prev
    Next
    INDEX
    Explanations

    subtle expressions of awareness and realization in personal narratives

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

    Lack of awareness or knowledge

    np_acts-logits-general · gemini-2.0-flash

    unaware of consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.55
    
    -0.52
     particulières
    -0.50
    ={({
    -0.49
    TokenNameDOT
    -0.49
    |>
    -0.47
    TagHelper
    -0.47
     Imagination
    -0.45
     aftermarket
    -0.44
     [],
    
    -0.44
    POSITIVE LOGITS
     unknowingly
    1.71
     unwittingly
    1.49
     unaware
    1.47
     unconsciously
    1.39
     unintentionally
    1.15
     unwit
    1.11
     subconsciously
    1.08
     oblivious
    1.08
     unconscious
    1.06
    不自
    1.05
    Activations Density 0.229%

    No Known Activations