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. 4-GEMMASCOPE-RES-16K
    6. 3397
    Prev
    Next
    INDEX
    Explanations

    parentheses and their contents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arşivlendi
    -0.60
     Pingback
    -0.55
    menuStrip
    -0.55
    shiro
    -0.53
     sobra
    -0.52
    zinger
    -0.52
    jsonwebtoken
    -0.51
    olisian
    -0.51
    økt
    -0.51
     ReSharper
    -0.50
    POSITIVE LOGITS
    WebMethod
    0.75
     referenties
    0.72
     utafitiHapana
    0.69
    Controllo
    0.68
    )
    0.66
    hoeddwyd
    0.66
    ?)
    0.61
    +#+#
    0.59
    RegistryLite
    0.58
    …)
    0.58
    Activations Density 0.891%

    No Known Activations