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 Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2463
    Prev
    Next
    INDEX
    Explanations

    references to communication systems and protocols

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

    "CS" abbreviation in technical contexts

    np_acts-logits-general · gemini-2.0-flash

    abbreviations or acronyms starting with CS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )});
    -0.72
    withIdentifier
    -0.71
    }();
    -0.70
    __':
    
    -0.69
     }}"></
    -0.68
    makeConstraints
    -0.68
    DispatchToProps
    -0.67
    ovács
    -0.66
    envolvimento
    -0.65
    Calais
    -0.65
    POSITIVE LOGITS
    WireFormatLite
    0.65
     Arne
    0.59
    ional
    0.59
    eriks
    0.58
     образом
    0.55
    holds
    0.55
    profen
    0.54
    OCCURRED
    0.54
    éric
    0.54
    Ű
    0.54
    Activations Density 0.484%

    No Known Activations