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. 8238
    Prev
    Next
    INDEX
    Explanations

    the legal terms and phrases related to arguments and contentions in legal contexts

    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
    ValueStyle
    -0.56
    ceedings
    -0.49
    apimachinery
    -0.47
    utilisons
    -0.47
     Amb
    -0.46
    Cubit
    -0.45
    قایناقلار
    -0.44
    doise
    -0.43
    #+#
    -0.43
    TheReal
    -0.42
    POSITIVE LOGITS
     believes
    0.67
     presumption
    0.66
     <<<<<<<<<<<<<<
    0.66
    abstractmethod
    0.65
     croire
    0.64
     وصلة
    0.64
     assertion
    0.63
     Behaup
    0.62
    findpost
    0.61
     Assumption
    0.61
    Activations Density 0.559%

    No Known Activations