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. 16-GEMMASCOPE-RES-16K
    6. 4675
    Prev
    Next
    INDEX
    Explanations

    modal verbs and their usage in various contexts

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

    German language text

    np_acts-logits-general · gemini-2.0-flash

    das + noun

    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
     ovvero
    -0.52
    ciler
    -0.51
     siap
    -0.51
    h
    -0.50
    in
    -0.50
    hi
    -0.49
     Vorteil
    -0.48
     ready
    -0.47
     dehors
    -0.47
    const
    -0.46
    POSITIVE LOGITS
    elfde
    0.75
    entai
    0.70
    glEnd
    0.69
    :]:
    0.68
    ništvo
    0.68
    __":
    0.67
    脚注の使い方
    0.67
    __':
    0.65
    nito
    0.63
     Neale
    0.63
    Activations Density 0.256%

    No Known Activations