© 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. 21-GEMMASCOPE-RES-16K
    11. 1063
    Prev
    Next
    INDEX
    Explanations

    elements related to modal verbs and their usage in context

    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
    TagMode
    -0.86
     myſelf
    -0.78
    ContentAlignment
    -0.74
    JspWriter
    -0.71
     pinulongan
    -0.67
    pushFollow
    -0.66
    UnusedPrivate
    -0.66
    دانشنامهٔ
    -0.63
     poffe
    -0.63
     itſelf
    -0.62
    POSITIVE LOGITS
    vieren
    0.48
     collect
    0.46
     select
    0.46
    selen
    0.46
     insure
    0.45
    zen
    0.45
    enable
    0.44
     happen
    0.44
    xen
    0.44
    Institutional
    0.42
    Activations Density 0.030%

    No Known Activations