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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Post
    5. 12-GEMMASCOPE-RES-1M
    6. 5
    Prev
    Next
    INDEX
    Explanations

    elements related to significant influence or impact within various contexts

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

    expressions or phrases related to uncertainty, questioning, or consideration of possibilities.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @nrbln
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.85
    ClientSize
    -0.79
    GEBURTSDATUM
    -0.79
    KURZBESCHREIBUNG
    -0.69
    ISupport
    -0.66
     beſt
    -0.65
     ordinaire
    -0.65
    StructEnd
    -0.65
    Activité
    -0.63
    ęku
    -0.63
    POSITIVE LOGITS
     smtplib
    0.43
    __":
    
    0.42
    なんですが
    0.41
     prim
    0.41
    porre
    0.41
    didReceive
    0.40
     именно
    0.38
     deles
    0.38
     المكتبه
    0.38
     Cuevas
    0.38
    Activations Density 0.013%

    No Known Activations