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. 14-GEMMASCOPE-RES-16K
    6. 7411
    Prev
    Next
    INDEX
    Explanations

    references and citations related to various topics, particularly in academic and botanical contexts

    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
     tulang
    -0.48
    Legături
    -0.45
     Special
    -0.45
     hear
    -0.43
     dokun
    -0.41
     stej
    -0.41
     khusus
    -0.41
    ste
    -0.41
     special
    -0.40
    ことを
    -0.40
    POSITIVE LOGITS
     Roskov
    1.17
    Personensuche
    0.98
    Portale
    0.94
    исленность
    0.92
    MigrationBuilder
    0.89
    Попис
    0.88
    principalTable
    0.86
     Waray
    0.84
     referenties
    0.82
    出版年
    0.82
    Activations Density 0.343%

    No Known Activations