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. 21-GEMMASCOPE-RES-16K
    6. 14927
    Prev
    Next
    INDEX
    Explanations

    terms related to software development and technical setups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.52
     Administrativna
    -0.48
     esternos
    -0.47
     arşivlendi
    -0.47
     ProtoMessage
    -0.46
     validamos
    -0.46
     bandou
    -0.46
     Baillargeon
    -0.45
     ivelany
    -0.44
     désolés
    -0.44
    POSITIVE LOGITS
    astify
    0.61
    rungsseite
    0.57
    mbggenerated
    0.41
     another
    0.40
     SOT
    0.40
     Peptide
    0.40
     anthem
    0.40
     separate
    0.39
    findpost
    0.39
    isContained
    0.38
    Activations Density 0.742%

    No Known Activations