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. 1-GEMMASCOPE-RES-16K
    6. 7473
    Prev
    Next
    INDEX
    Explanations

    expressions emphasizing clarity or certainty in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idental
    -0.58
     onCreateView
    -0.57
    dicionado
    -0.56
     NavController
    -0.54
    libft
    -0.54
    τουργ
    -0.53
     Bayard
    -0.53
     infest
    -0.53
     Khart
    -0.53
     GenerationType
    -0.53
    POSITIVE LOGITS
     clearly
    3.69
    clearly
    3.41
     Clearly
    3.15
    Clearly
    2.96
     claramente
    2.63
     clairement
    2.43
     chiaramente
    2.23
     plainly
    2.08
     duidelijk
    1.67
     eindeutig
    1.51
    Activations Density 0.196%

    No Known Activations