© 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-2-9B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 8001
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electronic components and their functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.69
    GEBURTSDATUM
    -0.68
     ब्रेकडाउन
    -0.68
    +#+
    -0.66
    ConstraintMaker
    -0.65
    
    -0.64
     nonUne
    -0.64
    /**
    -0.63
    MessageOf
    -0.61
     ostavi
    -0.60
    POSITIVE LOGITS
     blast
    0.29
    JTextField
    0.28
     Gustaf
    0.28
     tri
    0.27
     Ay
    0.27
     accredit
    0.27
    ächst
    0.27
     sum
    0.27
    водства
    0.26
    ńst
    0.26
    Activations Density 0.566%

    No Known Activations