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. 12599
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and court-related contexts

    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
    )_/¯
    -0.55
    avar
    -0.53
    хьтан
    -0.51
    PyTuple
    -0.51
    ropriate
    -0.50
    AVAN
    -0.49
    esercito
    -0.49
    󠁢
    -0.49
     AssemblyProduct
    -0.46
    podes
    -0.46
    POSITIVE LOGITS
     EconPapers
    0.77
    oredCriteria
    0.76
    XmlEnum
    0.70
    istoitu
    0.64
    EDEFAULT
    0.64
    +#+#
    0.64
     lenker
    0.64
     transfieras
    0.63
     оригіналу
    0.62
     مشين
    0.60
    Activations Density 1.551%

    No Known Activations