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. 3165
    Prev
    Next
    INDEX
    Explanations

    CSS properties and styles related to user interface elements

    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
    mybatisplus
    -0.90
     }</
    -0.83
    UnknownFields
    -0.82
    .)}
    -0.76
    ++]=
    -0.75
    المناصب
    -0.74
    ContentAlignment
    -0.74
    Demografie
    -0.74
    udadera
    -0.72
     AspNetCore
    -0.72
    POSITIVE LOGITS
    UMBIA
    0.44
    ferrer
    0.43
    meida
    0.42
     Barlow
    0.42
     di
    0.40
    "
    0.40
     vini
    0.39
    tagHelper
    0.39
     lại
    0.38
     tut
    0.38
    Activations Density 0.109%

    No Known Activations