© 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. 5026
    Prev
    Next
    INDEX
    Explanations

    modal verbs that indicate uncertainty or necessity

    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
    us
    -0.47
    li
    -0.45
     fald
    -0.45
    ili
    -0.43
    ca
    -0.42
     celles
    -0.41
    eck
    -0.40
     censorship
    -0.39
    ura
    -0.39
    amo
    -0.39
    POSITIVE LOGITS
    GraphicsUnit
    0.98
     unknownFields
    0.93
    Portály
    0.88
    AddTagHelper
    0.86
    apimachinery
    0.83
    ).__
    0.82
    rouvez
    0.82
    extAlignment
    0.82
     autorytatywna
    0.81
    posedge
    0.80
    Activations Density 1.018%

    No Known Activations