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. 2-GEMMASCOPE-RES-16K
    6. 6200
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "UTF" and related charset encodings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     joaat
    -0.56
    الحياه
    -0.56
     Alamos
    -0.53
     works
    -0.52
     erfolgreich
    -0.52
    ούν
    -0.52
    בודה
    -0.51
     âmes
    -0.50
    works
    -0.49
    دانشنامهٔ
    -0.48
    POSITIVE LOGITS
    UTF
    3.67
    utf
    2.35
     UTF
    2.17
     utf
    1.69
    Utf
    1.30
     Utf
    1.14
    charset
    1.00
     charset
    0.92
    ASCII
    0.73
    ########.
    0.73
    Activations Density 0.036%

    No Known Activations