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. 7-GEMMASCOPE-RES-16K
    6. 14717
    Prev
    Next
    INDEX
    Explanations

    references to individuals or entities with the prefix "Mc."

    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
    Portail
    -0.97
    ."</
    -0.89
    twimg
    -0.84
    Portale
    -0.83
    Бахар
    -0.81
    DebuggerNonUser
    -0.79
    GEBURTSDATUM
    -0.78
     autorité
    -0.77
     Olin
    -0.76
     Eaton
    -0.76
    POSITIVE LOGITS
    Mc
    1.68
     Mc
    1.62
    Mac
    1.42
     Mac
    1.42
     mac
    1.34
     McGu
    1.32
     mc
    1.27
    mac
    1.22
    mc
    1.19
     Macs
    1.18
    Activations Density 0.070%

    No Known Activations