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. 5-GEMMASCOPE-RES-16K
    6. 5325
    Prev
    Next
    INDEX
    Explanations

    configurations and specifications related to alignment and layout in web design or application development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -1.00
     للاسماء
    -0.97
    rungsseite
    -0.76
    RTDA
    -0.72
     चीज़ों
    -0.71
     utafitiHapana
    -0.71
    hyrchwyd
    -0.70
    UnknownFields
    -0.65
     विश्वसनीयता
    -0.64
     Wiktionnaire
    -0.63
    POSITIVE LOGITS
    stdc
    0.43
     tkinter
    0.42
     stop
    0.41
    Externé
    0.41
     blevet
    0.39
    IPE
    0.39
    deutschen
    0.39
    Джерело
    0.39
    migrationBuilder
    0.38
     Tercera
    0.38
    Activations Density 5.316%

    No Known Activations