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. 23-GEMMASCOPE-RES-16K
    6. 5767
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases about suitability and effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.72
    AndEndTag
    -0.72
    ValueStyle
    -0.69
    HasBeenSet
    -0.64
    Хьажоргаш
    -0.63
     Biôgrafia
    -0.62
    IVEREF
    -0.61
     Roskov
    -0.59
    lusconi
    -0.59
    Personendaten
    -0.59
    POSITIVE LOGITS
     ideal
    2.57
     perfect
    2.43
    ideal
    2.21
    Ideal
    2.13
     Ideal
    2.10
    perfect
    2.09
     ideale
    1.96
     suitable
    1.96
    Perfect
    1.89
     Perfect
    1.88
    Activations Density 0.318%

    No Known Activations