© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 3216
    Prev
    Next
    INDEX
    Explanations

    sections of text indicating changes or differences in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     westfalen
    -0.66
     ſind
    -0.64
     ſch
    -0.61
     ſche
    -0.61
     queſta
    -0.60
     mauva
    -0.59
    IBLIO
    -0.59
     Geſ
    -0.59
    chieht
    -0.59
     šaty
    -0.58
    POSITIVE LOGITS
    ---
    1.36
    ***
    1.28
     ***
    1.01
     ---
    0.98
    !!!
    0.96
    ###
    0.94
    xxx
    0.94
    III
    0.93
    iii
    0.93
    ???
    0.93
    Activations Density 0.312%

    No Known Activations