Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12569
    Prev
    Next
    INDEX
    Explanations

    references to freezing or frozen items and their characteristics

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

    associated with freezing or ice

    np_acts-logits-general · gemini-2.0-flash

    freezing, frozen states, ice

    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
    #+#
    -1.02
    SequentialGroup
    -0.84
     AssemblyCulture
    -0.79
    findpost
    -0.78
     propOrder
    -0.75
    WithMany
    -0.73
     OnInit
    -0.73
    GeneratedValue
    -0.71
     Swine
    -0.70
     مشين
    -0.69
    POSITIVE LOGITS
     freeze
    1.27
     froze
    1.16
     freezing
    1.16
     Freeze
    1.15
     ice
    1.12
     freezes
    1.10
     freezer
    1.06
     congel
    1.04
    freeze
    1.03
     thawed
    1.03
    Activations Density 0.196%

    No Known Activations