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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9235
    Prev
    Next
    INDEX
    Explanations

    references to the pronoun "or" in various contexts

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

    the word "or" when it appears between gendered pronouns like "his/her" in formal or legal writing.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.54
    enumi
    -0.50
     withal
    -0.46
     resourceCulture
    -0.43
    Népesség
    -0.42
     '\\;'
    -0.42
    +#+
    -0.41
    шкан
    -0.40
     tre
    -0.40
    참고
    -0.40
    POSITIVE LOGITS
    HasForeignKey
    0.47
    lccn
    0.46
     استنادى
    0.44
     gynhyrchwyd
    0.41
     kohdetta
    0.41
     Administrativna
    0.40
     виправивши
    0.39
    ulemon
    0.39
    Hers
    0.38
    Rohy
    0.38
    Activations Density 0.121%

    No Known Activations