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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 23-GEMMASCOPE-RES-16K
    6. 12380
    Prev
    Next
    INDEX
    Explanations

    mentions of the prefix "trans," indicating a focus on processes involving transfer, transformation, or transition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    žnost
    -0.55
    }{*}{}
    -0.54
    FontOfSize
    -0.49
    enumi
    -0.49
    readValue
    -0.49
    RuleContext
    -0.48
    CloseOperation
    -0.48
     EconPapers
    -0.47
    izr
    -0.47
     Administrativna
    -0.46
    POSITIVE LOGITS
    AutoresizingMask
    0.73
    Билгалдахарш
    0.67
     trans
    0.67
     onAnimation
    0.59
    trans
    0.57
     Transc
    0.56
    Trans
    0.54
    Ανα
    0.53
     caccia
    0.53
    missed
    0.53
    Activations Density 0.167%

    No Known Activations