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. 14948
    Prev
    Next
    INDEX
    Explanations

    references to previous sections and data points in a structured argument or analysis

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

    preceding sections or paragraphs

    np_acts-logits-general · gemini-2.0-flash

    previous section or paragraph

    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
    gnac
    -0.60
    رشف
    -0.54
    haustible
    -0.52
     miglia
    -0.51
    útbol
    -0.50
    ophys
    -0.50
    thral
    -0.48
     dietro
    -0.48
    ónde
    -0.48
    InputBorder
    -0.47
    POSITIVE LOGITS
    XmlEnum
    0.76
     <<<<<<<<<<<<<<
    0.73
    endphp
    0.58
    tagHelperRunner
    0.56
    Referencie
    0.55
     Walkover
    0.55
     AspNetCore
    0.55
     Moq
    0.54
    
    0.54
    Diweddarwch
    0.54
    Activations Density 0.702%

    No Known Activations