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. 4-GEMMASCOPE-RES-16K
    6. 11194
    Prev
    Next
    INDEX
    Explanations

    events and their subsequent developments or follow-ups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "}")
    -0.59
    CPtr
    -0.58
    ponses
    -0.57
    GraphicsUnit
    -0.51
     mappa
    -0.49
    ParallelGroup
    -0.47
    cross
    -0.46
     getBy
    -0.46
     समीक्षक
    -0.46
     grà
    -0.46
    POSITIVE LOGITS
    verwijspagina
    0.65
    MethodManager
    0.62
     histórica
    0.60
    +#+#
    0.57
    //};
    0.56
    zeiti
    0.56
     '\\;'
    0.56
    SourceChecksum
    0.55
    //}
    
    0.54
    HomeAsUp
    0.54
    Activations Density 0.440%

    No Known Activations