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. 21-GEMMASCOPE-RES-16K
    6. 12582
    Prev
    Next
    INDEX
    Explanations

    dialogue or interactions among characters, particularly involving inquiries and responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VizieR
    -0.55
     illustrazione
    -0.47
    ficha
    -0.46
    יתוף
    -0.45
     religione
    -0.45
    Seznam
    -0.45
     olması
    -0.45
     fasse
    -0.45
    sharing
    -0.44
    Accept
    -0.44
    POSITIVE LOGITS
     said
    1.47
     say
    1.32
     exclaimed
    1.32
    said
    1.27
     says
    1.26
     whispered
    1.24
     shouted
    1.20
     muttered
    1.20
    Said
    1.17
     exclaim
    1.15
    Activations Density 0.102%

    No Known Activations