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. 23-GEMMASCOPE-RES-16K
    6. 11187
    Prev
    Next
    INDEX
    Explanations

    structural elements in a layout design, specifically in user interface contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fromCharCode
    -0.56
     للمعارف
    -0.55
    estors
    -0.55
    FormField
    -0.53
    GraphicsUnit
    -0.53
     GoogleFonts
    -0.52
    WriteLiteral
    -0.51
    viewDidLoad
    -0.50
     Giles
    -0.49
    ostro
    -0.49
    POSITIVE LOGITS
    child
    1.14
     child
    1.03
    CHILD
    0.82
     Child
    0.82
     CHILD
    0.81
    Child
    0.81
     childs
    0.68
    childs
    0.57
    +#+
    0.57
    rungsseite
    0.56
    Activations Density 0.101%

    No Known Activations