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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3144
    Prev
    Next
    INDEX
    Explanations

    punctuations or closures in code syntax

    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
     prosegu
    -0.77
     Petrov
    -0.73
     riusc
    -0.69
     gambe
    -0.62
     desplaz
    -0.62
     Beg
    -0.59
    metz
    -0.57
     fianco
    -0.57
     Limb
    -0.57
    soon
    -0.57
    POSITIVE LOGITS
    */].
    0.94
    ].
    0.90
    [].
    0.86
     Tode
    0.80
    ]->
    0.78
    knapp
    0.77
     istore
    0.77
    "].
    0.76
    ]].
    0.76
    .].
    0.76
    Activations Density 0.132%

    No Known Activations