Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 4431
    Prev
    Next
    INDEX
    Explanations

    closing phrases in correspondence

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

    Formal email closings

    np_acts-logits-general · gemini-2.0-flash

    closing phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.60
    ่านั้น
    -0.55
    addCriterion
    -0.53
    beschreibung
    -0.53
    FTFY
    -0.53
    ệc
    -0.52
    jakan
    -0.51
    ærk
    -0.50
    неве
    -0.50
    ())->
    -0.49
    POSITIVE LOGITS
    Best
    1.25
    Regards
    1.25
     Regards
    1.24
     Sincerely
    1.23
    Sincerely
    1.20
     Best
    1.17
     best
    1.16
    Kind
    1.15
    Yours
    1.10
     Kind
    1.08
    Activations Density 0.132%

    No Known Activations