© 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. 9040
    Prev
    Next
    INDEX
    Explanations

    terms related to freezing and frozen states

    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
    httphttps
    -0.92
     AssemblyTitle
    -0.73
    ttemberg
    -0.71
    .*")]
    -0.69
     @"/
    -0.69
    PathVariable
    -0.68
     cartaz
    -0.66
    degard
    -0.65
     تانيه
    -0.64
    trabajo
    -0.64
    POSITIVE LOGITS
     freeze
    1.98
     Freeze
    1.85
     frozen
    1.74
     freezes
    1.72
    Freeze
    1.71
     freezing
    1.70
     froze
    1.69
    freeze
    1.64
     Freezing
    1.56
    Freezing
    1.55
    Activations Density 0.106%

    No Known Activations