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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 12624
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, actions, and their implications in various contexts

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

    Followed by "and"

    np_acts-logits-general · gemini-2.0-flash

    conjunctions in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )_/¯
    -0.81
    @",
    -0.77
     poveznice
    -0.70
    Personensuche
    -0.65
    >({
    -0.64
    hyrchwyd
    -0.63
     Vikipedi
    -0.63
    "):
    
    -0.61
    '):
    
    -0.60
    `.`
    -0.58
    POSITIVE LOGITS
     and
    3.40
     и
    1.52
    และ
    1.50
     và
    1.48
    and
    1.30
     &
    1.28
     및
    1.28
    および
    1.26
    性和
    1.25
     și
    1.20
    Activations Density 15.522%

    No Known Activations