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. 138
    Prev
    Next
    INDEX
    Explanations

    phrases that describe exceptional qualities and service-oriented attributes

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

    Follows a determiner or preposition

    np_acts-logits-general · gemini-2.0-flash

    best, tout vas, anyone, to be, death penalty

    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
     rendus
    -0.54
     étoit
    -0.50
     intermédiaire
    -0.49
    Referències
    -0.48
    decken
    -0.48
     oficiales
    -0.47
     africana
    -0.47
     nghiệp
    -0.47
     εί
    -0.46
     consistente
    -0.46
    POSITIVE LOGITS
     дописавши
    0.99
    webElementGuid
    0.80
    prefixer
    0.79
    yntaxException
    0.78
    RenderAtEndOf
    0.75
    IntoConstraints
    0.74
    
    0.73
     ModelExpression
    0.72
    Geplaatst
    0.72
     Administrativna
    0.71
    Activations Density 0.060%

    No Known Activations