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. 10-GEMMASCOPE-RES-16K
    6. 4517
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to programming, scripting, and software libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FetchType
    -0.47
     Colleg
    -0.46
    DATUM
    -0.46
     MotionEvent
    -0.43
    μβρίου
    -0.43
    itat
    -0.41
    Reduc
    -0.41
     Mudah
    -0.41
     geschehen
    -0.41
    jiang
    -0.41
    POSITIVE LOGITS
    twimg
    0.94
     nakalista
    0.94
     通販
    0.88
     Photocase
    0.82
    CodeAttribute
    0.70
    TagMode
    0.68
    NOPQRST
    0.68
    tagHelperRunner
    0.65
     الحره
    0.64
    VIAF
    0.64
    Activations Density 0.308%

    No Known Activations