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. 1433
    Prev
    Next
    INDEX
    Explanations

    patterned whitespace or empty spaces 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 @ 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
    EReference
    -0.64
    RUnlock
    -0.60
    uinal
    -0.56
    kmal
    -0.55
     Estrada
    -0.54
    داری
    -0.54
    ResumeLayout
    -0.53
    cripts
    -0.53
    .
    -0.53
    SerializeField
    -0.52
    POSITIVE LOGITS
     reaſon
    0.88
     diſt
    0.85
     uſed
    0.84
     quæ
    0.84
     houſe
    0.84
     purpoſe
    0.83
     pleaſure
    0.83
     obſ
    0.83
     deſt
    0.82
     abſ
    0.82
    Activations Density 0.176%

    No Known Activations