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. 15201
    Prev
    Next
    INDEX
    Explanations

    phrases regarding the allocation and importance of attention in research or practices

    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
    ViewImports
    -0.67
    uke
    -0.56
    ArgsConstructor
    -0.55
     kinematics
    -0.54
    mstyle
    -0.53
     ratify
    -0.51
     PyObject
    -0.50
     HasFactory
    -0.49
    EndInit
    -0.49
     Hole
    -0.49
    POSITIVE LOGITS
     placed
    0.92
     accorded
    0.79
     paid
    0.78
    placed
    0.71
     devoted
    0.71
     Placed
    0.69
    writeFieldEnd
    0.67
     given
    0.67
    paid
    0.66
    Placed
    0.65
    Activations Density 0.186%

    No Known Activations