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. 6286
    Prev
    Next
    INDEX
    Explanations

    URL patterns or references in the text

    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
     Efq
    -0.98
     pleaſure
    -0.98
     myſelf
    -0.92
     doubtnut
    -0.90
     itſelf
    -0.89
     raiſ
    -0.87
     Monfieur
    -0.86
     ſeveral
    -0.86
     Conſ
    -0.85
     Haarlem
    -0.83
    POSITIVE LOGITS
     /
    1.55
     /\
    1.04
     Mathis
    0.99
     /=
    0.98
    iwa
    0.94
     Rosenthal
    0.91
     /(\
    0.91
     Jansen
    0.85
     Pfeiffer
    0.85
     -
    0.84
    Activations Density 0.096%

    No Known Activations