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. 3-GEMMASCOPE-RES-16K
    6. 12014
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions or arrangements involving "for" and its occurrences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -1.25
     Theſe
    -1.07
    ftances
    -1.05
     ་་
    -1.04
    }")
    
    -1.04
     Monfieur
    -1.01
    Geplaatst
    -1.01
    SpringRunner
    -1.00
     متعلقه
    -1.00
    $.
    
    -1.00
    POSITIVE LOGITS
     For
    2.90
    For
    2.89
    FOR
    2.15
     FOR
    2.04
    for
    1.79
    To
    1.23
     Für
    1.20
     Для
    1.19
     To
    1.18
    Для
    1.14
    Activations Density 0.067%

    No Known Activations