© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 8672
    Prev
    Next
    INDEX
    Explanations

    elements related to value proposition and differentiation in business offerings

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

    "value" or "product."

    np_acts-logits-general · gemini-2.0-flash

    demonstrating value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.43
    CppMethod
    -0.43
    তথ্যসূত্র
    -0.41
    RegistryLite
    -0.41
    oriques
    -0.38
    mergeFrom
    -0.36
    WriteBarrier
    -0.36
    SequentialGroup
    -0.36
     calculées
    -0.36
     NSCoder
    -0.36
    POSITIVE LOGITS
     value
    0.98
     VALUE
    0.91
     Value
    0.85
     product
    0.82
    value
    0.76
     valeur
    0.75
    Value
    0.75
    VALUE
    0.74
     products
    0.73
     differentiation
    0.73
    Activations Density 0.235%

    No Known Activations