© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 6641
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "bes" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The token "bes"

    np_acts-logits-general · gemini-2.0-flash

    words starting with bes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MemoryWarning
    -0.84
     ActivatedRoute
    -0.72
    complexContent
    -0.59
    DrawerLayout
    -0.59
    forName
    -0.58
    
    -0.58
    esModule
    -0.58
    ndice
    -0.57
    Anmeldung
    -0.57
    phalt
    -0.57
    POSITIVE LOGITS
     Bes
    0.79
    Bes
    0.61
     bes
    0.56
    はじめに
    0.56
     megs
    0.54
    BES
    0.52
    bes
    0.51
     باخ
    0.51
    amazonaws
    0.50
    *************/
    0.49
    Activations Density 0.146%

    No Known Activations