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. 3-GEMMASCOPE-RES-16K
    6. 12538
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to legal matters and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.94
    parsedMessage
    -0.92
    Hentet
    -0.87
     enriquec
    -0.85
     reciprocity
    -0.85
    帖最后由
    -0.85
    UpInside
    -0.83
    Personensuche
    -0.83
    InjectAttribute
    -0.82
     виправивши
    -0.81
    POSITIVE LOGITS
     legal
    3.11
     Legal
    2.93
    Legal
    2.84
    legal
    2.68
     LEGAL
    2.65
    LEGAL
    2.45
     legales
    1.90
     legale
    1.87
     legally
    1.84
     légal
    1.51
    Activations Density 0.070%

    No Known Activations