© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 10848
    Prev
    Next
    INDEX
    Explanations

    descriptions of the condition of objects, particularly regarding their quality and state

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

    [Adjective] condition/shape

    np_acts-logits-general · gemini-2.0-flash

    quality of condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    secuencias
    -0.57
    UnknownFieldSet
    -0.55
    ftagPool
    -0.54
    migrationBuilder
    -0.49
     fraude
    -0.48
    ConverterFactory
    -0.48
     betweenstory
    -0.48
    dose
    -0.46
    ulong
    -0.46
    ModelSerializer
    -0.46
    POSITIVE LOGITS
     condition
    1.56
     shape
    1.34
    condition
    1.24
     Condition
    1.21
    Condition
    1.11
     CONDITION
    1.10
     Shape
    1.07
    shape
    1.06
     SHAPE
    0.99
     condición
    0.94
    Activations Density 0.158%

    No Known Activations