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. 23-GEMMASCOPE-RES-16K
    6. 11561
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal processes and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    herself
    -1.12
    himself
    -1.07
     Himself
    -0.99
     Itself
    -0.94
    themselves
    -0.93
    selves
    -0.93
     Оно
    -0.87
     himself
    -0.87
    itself
    -0.84
     herself
    -0.81
    POSITIVE LOGITS
     their
    1.52
     your
    1.52
     seu
    1.51
     his
    1.51
     seus
    1.48
     sua
    1.38
     své
    1.35
     свою
    1.34
     suas
    1.33
     своих
    1.24
    Activations Density 2.694%

    No Known Activations