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

    Neuronpedia

    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. 16-GEMMASCOPE-RES-16K
    11. 8255
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "condition" and its variations in various contexts

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

    "Condition" or "conditions" text

    np_acts-logits-general · gemini-2.0-flash

    condition expression or when

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FormBuilder
    -0.70
     VIAF
    -0.69
     Bam
    -0.69
    揄
    -0.68
     astray
    -0.68
     NDEBUG
    -0.66
    restle
    -0.66
     Gemma
    -0.65
     respiro
    -0.65
     Jagger
    -0.65
    POSITIVE LOGITS
     conditions
    1.75
     Conditions
    1.60
    conditions
    1.58
    Conditions
    1.52
    Condition
    1.43
     condition
    1.43
     CONDITIONS
    1.42
     Condition
    1.38
    condition
    1.32
     CONDITION
    1.27
    Activations Density 0.083%

    No Known Activations