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. 8-GEMMASCOPE-RES-16K
    6. 8009
    Prev
    Next
    INDEX
    Explanations

    references to regular expressions and their matching capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.76
    ]")]
    -0.63
    Zé
    -0.61
    HasAnnotation
    -0.58
    tencent
    -0.55
     onBind
    -0.51
     Furn
    -0.50
    randomUUID
    -0.49
    requireNonNull
    -0.48
    ValueGeneration
    -0.47
    POSITIVE LOGITS
    География
    0.63
     lọc
    0.62
     selectivity
    0.60
     sieve
    0.60
     kaarangay
    0.58
     RegExp
    0.58
     Filters
    0.57
    bnf
    0.56
     dilated
    0.56
    Controllo
    0.56
    Activations Density 0.747%

    No Known Activations