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. 19-GEMMASCOPE-RES-16K
    6. 3636
    Prev
    Next
    INDEX
    Explanations

    formal elements related to organizational processes and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -0.43
     F
    -0.42
     P
    -0.41
    FTS
    -0.40
     
    -0.39
     B
    -0.39
    da
    -0.39
    この
    -0.39
     W
    -0.38
     Philippines
    -0.38
    POSITIVE LOGITS
     myſelf
    1.20
     ſtate
    1.13
     Monfieur
    1.10
     pleaſure
    1.10
     Majefty
    1.09
    CloseOperation
    1.05
     ſche
    1.03
     purpoſe
    1.03
     fubject
    1.03
     Jefus
    1.01
    Activations Density 0.562%

    No Known Activations