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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2706
    Prev
    Next
    INDEX
    Explanations

    references to historical achievements or milestones, especially regarding notable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onAttach
    -0.53
    สุข
    -0.44
    bux
    -0.40
    ContentAlignment
    -0.40
     qualidade
    -0.40
    เหล
    -0.39
     const
    -0.38
     X
    -0.38
    лии
    -0.38
     comprends
    -0.38
    POSITIVE LOGITS
     poffe
    1.08
     himſelf
    1.03
     myſelf
    0.99
     themſelves
    0.98
     fubject
    0.93
     ſeveral
    0.92
    SequentialGroup
    0.92
     unprecedented
    0.91
     itſelf
    0.90
     houſe
    0.90
    Activations Density 0.206%

    No Known Activations