Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 12934
    Prev
    Next
    INDEX
    Explanations

    instances of the 'endl' output stream manipulator in C++ code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.84
    jshint
    -0.59
    Acti
    -0.58
    ('/:
    -0.58
     tü
    -0.56
     Acti
    -0.54
     Stä
    -0.54
    כשיו
    -0.53
    ั่ว
    -0.53
    griff
    -0.52
    POSITIVE LOGITS
     endl
    2.08
    endl
    1.92
     يتيمه
    1.25
    NewLine
    0.92
     bezeichneter
    0.87
     Efq
    0.74
     Egyptians
    0.70
    )‏
    0.70
     MemoryStream
    0.69
    LEncoder
    0.67
    Activations Density 0.022%

    No Known Activations