© 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. 5-GEMMASCOPE-RES-16K
    11. 5347
    Prev
    Next
    INDEX
    Explanations

    statements or phrases concerning minimum requirements or thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sp
    -0.58
    kadang
    -0.58
     szól
    -0.57
     âgées
    -0.56
    Sp
    -0.55
    häuse
    -0.55
    often
    -0.55
    SP
    -0.55
     meds
    -0.55
     lập
    -0.54
    POSITIVE LOGITS
    maximum
    1.69
     maximum
    1.64
     Maximum
    1.63
    Maximum
    1.60
    MAXIMUM
    1.57
     MAXIMUM
    1.55
    minimum
    1.47
    Minimum
    1.41
     máxima
    1.37
     minimum
    1.35
    Activations Density 0.076%

    No Known Activations