© 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. 14-GEMMASCOPE-RES-16K
    11. 4535
    Prev
    Next
    INDEX
    Explanations

    the frequency of numerical values represented in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.08
     myſelf
    -1.08
    InjectAttribute
    -1.07
    rungsseite
    -1.05
     ―――――
    -1.04
     poffible
    -1.04
     للاسماء
    -1.01
     pleaſure
    -1.00
     AssemblyVersion
    -0.97
     Monfieur
    -0.96
    POSITIVE LOGITS
    0.67
    [toxicity=0]
    0.54
    /

    0.54
     mo
    0.52
    󠁢
    0.52
     or
    0.52
      (
    0.50
     atau
    0.50
     \&
    0.50
     Tw
    0.49
    Activations Density 0.533%
    No Known Activations