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. 5629
    Prev
    Next
    INDEX
    Explanations

    legal terms related to rights and judicial proceedings

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

    Possessive pronoun before "rights"

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns and constitutional rights

    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
     كومونز
    -0.53
     cref
    -0.52
    HasAnnotation
    -0.52
    rawDesc
    -0.51
    かで
    -0.51
    lani
    -0.50
    jek
    -0.49
     cyclo
    -0.48
     khảo
    -0.48
    igshid
    -0.47
    POSITIVE LOGITS
     right
    2.19
     rights
    2.15
    right
    1.84
     Right
    1.80
    rights
    1.76
    Right
    1.76
     Rights
    1.66
     RIGHT
    1.65
     RIGHTS
    1.63
    Rights
    1.54
    Activations Density 0.433%

    No Known Activations