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. 13972
    Prev
    Next
    INDEX
    Explanations

    instances of the word "even" and its various contexts

    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
     dönt
    -0.61
     BaseActivity
    -0.61
     Juifs
    -0.60
     urma
    -0.60
    RuleContext
    -0.58
     @"";
    -0.58
    localctx
    -0.55
    /***/
    -0.55
    artamento
    -0.54
    estanding
    -0.54
    POSITIVE LOGITS
     sogar
    1.13
     even
    1.07
     addirittura
    1.04
     zelfs
    0.97
    even
    0.89
     persino
    0.82
    EVEN
    0.82
    Bahkan
    0.81
     EVEN
    0.80
    Even
    0.79
    Activations Density 0.251%

    No Known Activations