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. 11-GEMMASCOPE-RES-16K
    6. 1783
    Prev
    Next
    INDEX
    Explanations

    concepts related to developmental outcomes and associated factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     leçons
    -0.55
    thin
    -0.49
     New
    -0.47
     siker
    -0.45
     részt
    -0.45
    kse
    -0.45
     jueces
    -0.45
     Thin
    -0.45
    мит
    -0.44
    Thin
    -0.44
    POSITIVE LOGITS
    httphttps
    1.17
    regarding
    1.02
     calendriers
    1.02
     noqa
    1.00
    BufferException
    0.99
     regards
    0.98
    SuppressMessage
    0.98
     hinsichtlich
    0.98
    ResumeLayout
    0.96
     שוליים
    0.95
    Activations Density 0.180%

    No Known Activations