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. 10420
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to business transactions and corporate relationships

    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
     Bioaccumulative
    -0.59
    __':
    -0.49
    __":
    -0.48
    COLLE
    -0.48
    lių
    -0.47
     NCAA
    -0.46
    >//
    -0.46
    initializeApp
    -0.46
     Customer
    -0.46
     vero
    -0.45
    POSITIVE LOGITS
    fjspx
    0.74
    yntaxException
    0.64
     المتحدة
    0.58
    RenderAtEndOf
    0.57
     تضيفلها
    0.57
    hells
    0.56
     Administrativna
    0.56
     informée
    0.55
     &___
    0.55
    ępo
    0.55
    Activations Density 0.236%

    No Known Activations