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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3380
    Prev
    Next
    INDEX
    Explanations

    terms related to legal appeals and court processes

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

    "appeal" or its inflections

    np_acts-logits-general · gemini-2.0-flash

    notice of appeal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.52
    Synchronized
    -0.52
    Portail
    -0.51
    parsedMessage
    -0.50
    Personendaten
    -0.49
    fromnode
    -0.49
    PropertyChanging
    -0.47
     maravillas
    -0.46
     moustache
    -0.45
     shutting
    -0.45
    POSITIVE LOGITS
     appeal
    1.41
     appeals
    1.31
     Appeal
    1.31
    appeal
    1.29
    Appeal
    1.28
     appealed
    1.21
     APPEAL
    1.18
     Appeals
    1.13
    Appe
    1.11
     appealing
    1.10
    Activations Density 1.157%

    No Known Activations