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. 41-GEMMASCOPE-RES-16K
    6. 7218
    Prev
    Next
    INDEX
    Explanations

    references to communication and inquiries within discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.49
    transQ
    -0.49
    ParallelGroup
    -0.45
    DIPSETTING
    -0.44
    cyklopedia
    -0.44
    ьаж
    -0.41
     становника
    -0.41
    LookAnd
    -0.40
    >//
    -0.39
    awtextra
    -0.39
    POSITIVE LOGITS
     post
    1.66
     upload
    1.20
     repost
    1.16
    post
    1.14
     пост
    1.06
     publish
    1.03
     Post
    1.02
    Post
    1.01
     posting
    1.00
     POST
    0.90
    Activations Density 0.609%

    No Known Activations