© 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-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5899
    Prev
    Next
    INDEX
    Explanations

    terms related to freezing and ice formation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.60
    tagHelperRunner
    -0.54
     تعدى
    -0.49
    TargetException
    -0.49
    RuleContext
    -0.48
    exitRule
    -0.48
    SourceChecksum
    -0.48
     journaux
    -0.47
    errHandler
    -0.47
     ladrillo
    -0.47
    POSITIVE LOGITS
     ice
    1.09
     snow
    1.03
     freezing
    1.02
     Ice
    1.00
    Ice
    0.94
    snow
    0.94
    Snow
    0.93
    ❄️
    0.91
    ☃
    0.91
     Snow
    0.90
    Activations Density 0.520%

    No Known Activations