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. 13295
    Prev
    Next
    INDEX
    Explanations

    terms related to the interactions and effects of biological components or substances

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

    Prepositions followed by nouns

    np_acts-logits-general · gemini-2.0-flash

    formation, cAMP, metabolic, phase, production

    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
     initComponents
    -0.63
    +#+
    -0.62
     AttributeSet
    -0.56
    Referanser
    -0.54
    Cursors
    -0.54
    ArrowToggle
    -0.54
    Ern
    -0.50
     Hors
    -0.49
     CMY
    -0.49
    تاح
    -0.49
    POSITIVE LOGITS
    }]
    
    0.68
    anthes
    0.58
    __(/*!
    0.58
     Bundesrepublik
    0.56
     quæ
    0.55
    億円
    0.55
     recommandons
    0.55
    writeValue
    0.55
    亿美元
    0.54
    TestingModule
    0.54
    Activations Density 0.685%

    No Known Activations