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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 12581
    Prev
    Next
    INDEX
    Explanations

    alphanumeric sequences and potential formatting or coding characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hag
    -0.53
     resid
    -0.53
    AddAttribute
    -0.52
    στε
    -0.51
    Substring
    -0.51
     Yer
    -0.51
    AA
    -0.50
     todays
    -0.49
    resid
    -0.48
    Mord
    -0.48
    POSITIVE LOGITS
    tagHelperRunner
    0.86
    الإنجليزية
    0.80
    -------------</
    0.78
    enumi
    0.73
    তথ্যসূত্র
    0.73
    出版年
    0.72
     gynhyrchwyd
    0.67
    isSuccessful
    0.65
    VersionUID
    0.65
    NewUrlParser
    0.63
    Activations Density 0.072%

    No Known Activations