© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 1906
    Prev
    Next
    INDEX
    Explanations

    packaging and container-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EXTERN
    -0.55
     mema
    -0.54
    GOTREF
    -0.53
    hline
    -0.48
    ineno
    -0.48
    lą
    -0.47
    Mixed
    -0.46
     mixed
    -0.46
    cademia
    -0.46
    ForValue
    -0.45
    POSITIVE LOGITS
     Packaging
    0.72
    httphttps
    0.70
     packaging
    0.69
    AsUp
    0.69
    packaging
    0.67
    Packaging
    0.64
    containers
    0.56
     wireType
    0.56
     Plastik
    0.55
     Verpackung
    0.54
    Activations Density 0.309%

    No Known Activations