© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8797
    Prev
    Next
    INDEX
    Explanations

    terms related to maximum and minimum values or thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Min
    -0.49
     Min
    -0.43
    writing
    -0.41
    tierrez
    -0.39
    écri
    -0.37
    flying
    -0.36
     min
    -0.36
    ierungs
    -0.36
    jectable
    -0.35
    vician
    -0.35
    POSITIVE LOGITS
     maximum
    3.45
    maximum
    3.20
    Maximum
    3.03
     Maximum
    3.02
     MAXIMUM
    2.61
    MAXIMUM
    2.48
     maksimum
    2.25
     máxima
    2.05
     максима
    2.05
     maximale
    2.03
    Activations Density 0.159%

    No Known Activations