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. 15-GEMMASCOPE-RES-16K
    6. 12929
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental and legal contexts, especially focusing on land use and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     دیکھیے
    -0.52
    </h1>
    -0.47
     solusi
    -0.46
    IVEREF
    -0.45
     oeufs
    -0.44
    antMatchers
    -0.42
    U
    -0.41
    Intial
    -0.40
     serius
    -0.40
     ,
    -0.40
    POSITIVE LOGITS
    yntaxException
    0.78
    setVerticalGroup
    0.77
     Administrativna
    0.73
    esgue
    0.71
    ſelf
    0.70
     bershka
    0.70
    Fprintf
    0.69
    GEBURTSDATUM
    0.69
    iprot
    0.68
     ProtoMessage
    0.67
    Activations Density 0.706%

    No Known Activations