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. 2-GEMMASCOPE-RES-16K
    6. 6836
    Prev
    Next
    INDEX
    Explanations

    HTML elements related to user interface components

    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
    <
    -0.89
     <
    -0.83
    -
    -0.79
    >
    -0.74
    "><
    -0.69
    ">
    -0.63
     (
    -0.61
     
    -0.61
     p
    -0.59
    ><
    -0.58
    POSITIVE LOGITS
     itſelf
    1.43
     myſelf
    1.38
    expandindo
    1.31
     Monfieur
    1.31
    ſelf
    1.27
    IsMutable
    1.26
     pleaſure
    1.24
     Jefus
    1.18
     Efq
    1.17
     iſt
    1.13
    Activations Density 0.645%

    No Known Activations