© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 9394
    Prev
    Next
    INDEX
    Explanations

    links to external resources or references related to examples and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AlterField
    -0.79
    '){
    -0.78
    '},
    -0.76
    Cyfeiriadau
    -0.74
    contentLoaded
    -0.69
    sidemargin
    -0.69
     Савезне
    -0.69
     disambiguazione
    -0.68
    '):
    -0.66
    ModelForm
    -0.65
    POSITIVE LOGITS
     https
    2.42
     http
    2.26
    https
    2.26
    http
    2.10
    ttps
    1.47
     www
    1.43
     link
    1.35
     LINK
    1.21
    link
    1.20
     Link
    1.17
    Activations Density 0.598%

    No Known Activations