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. 17-GEMMASCOPE-RES-16K
    6. 5924
    Prev
    Next
    INDEX
    Explanations

    sections containing statistical data or metrics related to studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kan
    -0.65
     mot
    -0.64
    (!__
    -0.63
     }^{\
    -0.63
    ikan
    -0.63
    paramref
    -0.63
     to
    -0.62
     k
    -0.60
    kan
    -0.60
     ${
    -0.59
    POSITIVE LOGITS
     myſelf
    1.26
     itſelf
    1.23
     doubtnut
    1.15
     Houſe
    1.08
     greateſt
    1.08
     Anſ
    1.07
     Jefus
    1.07
     Eſ
    1.07
     Conſ
    1.06
     pleaſure
    1.05
    Activations Density 0.983%

    No Known Activations