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. 22-GEMMASCOPE-RES-16K
    6. 10897
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to punishment and legal ramifications

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

    after "be", "been", or similar verb

    np_acts-logits-general · gemini-2.0-flash

    legally imposed, inflicted, applied

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Abandon
    -0.45
     maît
    -0.45
    nsito
    -0.44
     préoccup
    -0.44
     rembour
    -0.44
    Dead
    -0.42
     Dead
    -0.42
    Glorious
    -0.41
     Formed
    -0.40
     Killed
    -0.40
    POSITIVE LOGITS
     imposed
    1.45
     inflicted
    1.32
     applied
    1.20
     levied
    1.13
    imposed
    1.08
     bestowed
    1.06
     imposition
    1.06
    applied
    1.04
     inflict
    1.00
     impose
    0.99
    Activations Density 0.569%

    No Known Activations