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. 5-GEMMASCOPE-RES-16K
    6. 7419
    Prev
    Next
    INDEX
    Explanations

    expressions of personal perspective and emotions

    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
     yourself
    -0.76
     you
    -0.67
     your
    -0.67
    yourself
    -0.64
    you
    -0.63
    your
    -0.63
     YOURSELF
    -0.55
    CloseOperation
    -0.55
     Yourself
    -0.55
    principalColumn
    -0.53
    POSITIVE LOGITS
     CURIAM
    0.69
    Xna
    0.65
    Autoritní
    0.65
    Демографія
    0.61
    ropoda
    0.60
     Bourgoin
    0.60
    ptures
    0.59
     Wicidata
    0.59
    cèse
    0.56
    BeginContext
    0.56
    Activations Density 0.355%

    No Known Activations