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. 24-GEMMASCOPE-RES-16K
    6. 4794
    Prev
    Next
    INDEX
    Explanations

    specific legal terminology and references from court documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "except" or "order" regarding legal precedential effect

    np_acts-logits-general · gemini-2.0-flash

    except under

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    queryInterface
    -0.72
    jsonwebtoken
    -0.71
    InitVars
    -0.68
     MonoBehaviour
    -0.67
    SourceChecksum
    -0.65
    rawDesc
    -0.64
    lineno
    -0.64
    StoryboardSegue
    -0.63
    WriteTagHelper
    -0.63
     المعيارى
    -0.63
    POSITIVE LOGITS
    nien
    0.49
     pubblici
    0.47
    شوف
    0.44
     fausse
    0.43
     leçons
    0.41
    push
    0.41
     origines
    0.41
     VIAF
    0.41
    siapkan
    0.40
     pertes
    0.40
    Activations Density 0.136%

    No Known Activations