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. 23-GEMMASCOPE-RES-16K
    6. 11227
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their actions or presence

    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
    ilarang
    -0.47
    Brainz
    -0.46
     spørs
    -0.45
    ificantly
    -0.45
     orienti
    -0.44
     vectorielle
    -0.44
     alvor
    -0.43
     vervangen
    -0.43
     réjou
    -0.42
    interact
    -0.42
    POSITIVE LOGITS
    tvguidetime
    0.75
    HasAnnotation
    0.71
     تضيفلها
    0.69
     impose
    0.66
     bestow
    0.66
     besto
    0.65
    脚注の使い方
    0.62
     wrought
    0.62
     impart
    0.61
     imposes
    0.60
    Activations Density 0.257%

    No Known Activations