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-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11435
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.58
     IBOutlet
    -0.56
    AsUp
    -0.54
     ujednoznacz
    -0.47
    كويكب
    -0.46
    SourceChecksum
    -0.45
    BASEPATH
    -0.45
    Personensuche
    -0.44
    migrationBuilder
    -0.43
    FTFY
    -0.43
    POSITIVE LOGITS
    yntaxException
    0.58
    новништво
    0.48
    ConstraintMaker
    0.47
    ด้าน
    0.47
     propOrder
    0.46
    UCE
    0.43
    Portály
    0.43
     történ
    0.43
     való
    0.42
    idus
    0.42
    Activations Density 1.137%

    No Known Activations