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. 11027
    Prev
    Next
    INDEX
    Explanations

    references to "stars," particularly in the context of ratings and recognitions

    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
     Cuenca
    -0.86
     ivelany
    -0.83
     photolibrary
    -0.82
     ALC
    -0.78
    expandindo
    -0.78
     ③
    -0.77
     sledge
    -0.77
     RDC
    -0.76
     Bourgoin
    -0.76
     pinulongan
    -0.76
    POSITIVE LOGITS
     Star
    2.72
     star
    2.64
    Star
    2.51
     STAR
    2.44
    star
    2.43
     stars
    2.39
     Stars
    2.31
    STAR
    2.25
    stars
    2.16
    Stars
    2.15
    Activations Density 0.063%

    No Known Activations