© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 10505
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussing conditions or parameters in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     New
    -0.49
    edy
    -0.48
     leçons
    -0.46
    мит
    -0.46
     Álvarez
    -0.46
     pluie
    -0.46
     részt
    -0.46
     síntomas
    -0.45
     truco
    -0.45
     chaleco
    -0.44
    POSITIVE LOGITS
    httphttps
    1.10
    SuppressMessage
    1.09
    ResumeLayout
    1.07
     regards
    1.06
    regarding
    1.06
     GenerationType
    1.05
     hinsichtlich
    1.05
     noqa
    1.03
    ########.
    0.99
     snippetHide
    0.99
    Activations Density 0.153%

    No Known Activations