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. 21-GEMMASCOPE-RES-16K
    6. 12553
    Prev
    Next
    INDEX
    Explanations

    references to authority figures and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringBootTest
    -0.75
    TagMode
    -0.71
     snippetHide
    -0.69
     rospy
    -0.64
     pleaſure
    -0.62
    )++;
    -0.61
    ^(@)
    -0.61
    OptionsMenu
    -0.61
    IonicModule
    -0.60
     defStyle
    -0.60
    POSITIVE LOGITS
     into
    0.91
     back
    0.72
     on
    0.70
     onto
    0.67
     ahead
    0.66
     behind
    0.65
     down
    0.64
     up
    0.61
     aside
    0.60
     against
    0.58
    Activations Density 0.123%

    No Known Activations