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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 3045
    Prev
    Next
    INDEX
    Explanations

    terms related to the implementation of strategies or plans

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

    "implement"

    np_acts-logits-general · gemini-2.0-flash

    implementing strategic plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hésite
    -0.54
     renseignements
    -0.50
    SEGUIR
    -0.48
    ContextHolder
    -0.48
     berapa
    -0.47
    fancybox
    -0.45
    piración
    -0.45
     curiosidad
    -0.44
     deudas
    -0.44
     namorados
    -0.44
    POSITIVE LOGITS
     implementation
    1.81
     implement
    1.70
     Implementation
    1.63
     implementing
    1.62
     Implement
    1.59
    implementation
    1.58
     implemented
    1.56
    implement
    1.55
    Implementation
    1.55
    Implementing
    1.48
    Activations Density 0.135%

    No Known Activations