© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14097
    Prev
    Next
    INDEX
    Explanations

    structured code elements and definitions in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.70
    CGRectMake
    -0.57
    GEBURTSDATUM
    -0.56
    Πηγή
    -0.55
    닝
    -0.53
    ardless
    -0.52
     &___
    -0.51
    astéro
    -0.50
    ropoda
    -0.50
     AttributeSet
    -0.49
    POSITIVE LOGITS
     private
    2.74
    private
    2.56
     Private
    2.21
     PRIVATE
    2.15
    Private
    2.15
     privé
    2.03
    PRIVATE
    1.97
     privada
    1.96
     privat
    1.94
     privata
    1.89
    Activations Density 0.174%

    No Known Activations