© 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. 5-GEMMASCOPE-RES-16K
    11. 3710
    Prev
    Next
    INDEX
    Explanations

    multi-line comments in programming and markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prohibido
    -0.59
    TextWatcher
    -0.51
     beginnetje
    -0.50
    cloudflare
    -0.48
    bootstrapcdn
    -0.47
    stateParams
    -0.47
    pr
    -0.47
    ptic
    -0.47
     transparan
    -0.46
    prefixer
    -0.45
    POSITIVE LOGITS
     *"
    0.81
     *@
    0.77
    IUrlHelper
    0.70
     autorytatywna
    0.67
    MemoryWarning
    0.66
    enumii
    0.66
     >=",
    0.65
    ftagPool
    0.62
     betweenstory
    0.62
    writeFieldEnd
    0.62
    Activations Density 0.058%

    No Known Activations