© 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. 12-GEMMASCOPE-RES-16K
    6. 5685
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to synthesized materials or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 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
    
    -0.60
     EClass
    -0.59
    IntoConstraints
    -0.54
     TextAppearance
    -0.51
     kasarigan
    -0.47
    ArrowToggle
    -0.44
    ніципалі
    -0.44
     FetchType
    -0.43
    HostException
    -0.42
    WireFormatLite
    -0.42
    POSITIVE LOGITS
     obtained
    0.56
     resultant
    0.53
     obtenidos
    0.51
     generated
    0.48
    obtained
    0.47
     obtenido
    0.47
    created
    0.46
     formed
    0.45
    derived
    0.45
     zís
    0.45
    Activations Density 1.272%

    No Known Activations