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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16286
    Prev
    Next
    INDEX
    Explanations

    words related to "al," particularly in the context of names or identifiers

    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
    ніципалі
    -0.88
     createSprite
    -0.80
    Hochspringen
    -0.79
     مواليد
    -0.77
    complexContent
    -0.76
    jsxFileName
    -0.75
    AndroidJUnit
    -0.73
    StructEnd
    -0.72
    OGND
    -0.71
    CopyWith
    -0.70
    POSITIVE LOGITS
     al
    2.12
     AL
    2.10
     Al
    1.99
    Al
    1.83
    AL
    1.65
    al
    1.42
     Alg
    1.36
     Alb
    1.24
     Ala
    1.23
    アル
    1.22
    Activations Density 0.179%

    No Known Activations