Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-GEMMASCOPE-RES-16K
    6. 15355
    Prev
    Next
    INDEX
    Explanations

    structural elements in code or data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.66
    ionali
    -0.55
    دانشنامهٔ
    -0.53
    تقاوى
    -0.52
    mondo
    -0.51
     jsPsych
    -0.50
     uLocal
    -0.50
     auxquels
    -0.48
    jay
    -0.47
     utafitiHapana
    -0.46
    POSITIVE LOGITS
    mapStateToProps
    0.91
    SourceChecksum
    0.76
     AssemblyTitle
    0.75
     विश्वसनीयता
    0.71
    __(/*!
    0.70
    ябре
    0.67
    ГЛА
    0.65
    forName
    0.64
    DataAnnotations
    0.61
    ]")]
    0.60
    Activations Density 0.355%

    No Known Activations