© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 3726
    Prev
    Next
    INDEX
    Explanations

    C++ programming language components and syntax elements in the code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]--;
    -0.68
    twimg
    -0.65
    endpush
    -0.65
    Hochspringen
    -0.64
    timewa
    -0.58
    ljeno
    -0.56
     nonUne
    -0.56
     ),
    
    -0.55
    Skocz
    -0.54
    sibilità
    -0.53
    POSITIVE LOGITS
     AssemblyCulture
    0.88
    ViewFeatures
    0.67
     SafeMath
    0.62
    stdc
    0.60
     cellspacing
    0.60
    ArgsConstructor
    0.57
     nhiên
    0.56
    ActivityResult
    0.56
     dönt
    0.56
     FormsModule
    0.54
    Activations Density 0.047%

    No Known Activations