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. 7-GEMMASCOPE-RES-16K
    6. 8867
    Prev
    Next
    INDEX
    Explanations

    terms related to web development and CSS specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //});
    -0.71
    তথ্যসূত্র
    -0.70
    kulum
    -0.70
     InputDecoration
    -0.69
     PATIENT
    -0.62
    bingen
    -0.59
    HICLE
    -0.59
    AndEndTag
    -0.58
    いかに
    -0.56
    TextNode
    -0.56
    POSITIVE LOGITS
    omitempty
    1.00
     للاسماء
    0.92
     (!__
    0.79
    PointerException
    0.77
    usr
    0.77
    FieldDescriptor
    0.76
    UnusedPrivate
    0.74
     ModelExpression
    0.73
    InteropServices
    0.72
    queryInterface
    0.71
    Activations Density 0.013%

    No Known Activations