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

    Neuronpedia

    APICircuit 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. 0-GEMMASCOPE-RES-16K
    6. 3348
    Prev
    Next
    INDEX
    Explanations

    words relating to the concept of "digging" or exploration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.78
     iſt
    -0.69
     defStyleAttr
    -0.69
     Majefty
    -0.69
    những
    -0.69
    naphthal
    -0.68
    ſelf
    -0.67
    راتيج
    -0.66
    abuena
    -0.65
    มาณ
    -0.65
    POSITIVE LOGITS
     dig
    0.94
    Dig
    0.94
     Dig
    0.87
    ن
    0.85
    dig
    0.83
    ן
    0.74
    े
    0.70
    न
    0.63
    су
    0.63
    DIG
    0.59
    Activations Density 0.219%

    No Known Activations