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. 24-GEMMASCOPE-RES-16K
    6. 16311
    Prev
    Next
    INDEX
    Explanations

    references to video games and their features

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

    Preceding verbs/auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    common factor / exert influence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "]);
    
    -0.61
    ")){
    
    -0.60
    '],
    
    -0.60
    ագրություններ
    -0.59
     مرئيه
    -0.58
    "])
    
    -0.58
    "],
    
    -0.57
    .",
    
    -0.57
    حوالہ
    -0.56
    )}
    
    -0.55
    POSITIVE LOGITS
    Nosotros
    0.77
    Erst
    0.63
     cardinal
    0.61
     encephal
    0.60
     CGPoint
    0.60
     heb
    0.60
    rard
    0.59
     Erst
    0.59
    DockStyle
    0.59
     chemic
    0.58
    Activations Density 0.063%

    No Known Activations