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. 13-GEMMASCOPE-RES-16K
    6. 680
    Prev
    Next
    INDEX
    Explanations

    phrases related to research methodologies and findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.58
     nakalista
    -0.56
    complexContent
    -0.49
    atissimo
    -0.48
    ][-
    -0.48
    __*/
    -0.47
    kPa
    -0.47
    celes
    -0.47
    
    -0.47
    bibitem
    -0.46
    POSITIVE LOGITS
    setVerticalGroup
    0.86
    Искәрмәләр
    0.68
    RectangleBorder
    0.64
    CGRectMake
    0.63
    MessageTagHelper
    0.62
     fleste
    0.62
     Basically
    0.61
     flesta
    0.58
    StateException
    0.56
     gddr
    0.56
    Activations Density 0.567%

    No Known Activations