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. 2-GEMMASCOPE-RES-16K
    6. 1126
    Prev
    Next
    INDEX
    Explanations

    HTML character entities and their formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -1.11
    TintMode
    -1.09
     Roskov
    -0.99
    AddTagHelper
    -0.98
     Bourgoin
    -0.96
    mybatisplus
    -0.96
    adaptiveStyles
    -0.95
    ItemBackground
    -0.95
    OGND
    -0.95
     ExecuteAsync
    -0.94
    POSITIVE LOGITS
     \
    0.77
    \
    0.69
    <0xF0>
    0.65
     $\
    0.63
    P
    0.59
    operator
    0.58
    <0xE1>
    0.58
    A
    0.57
     A
    0.57
    _{\
    0.56
    Activations Density 0.237%

    No Known Activations