© 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. 10-GEMMASCOPE-RES-16K
    11. 13415
    Prev
    Next
    INDEX
    Explanations

    references to quantities or frequencies, particularly the word "many" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AfterClass
    -0.84
     FLA
    -0.68
     dovrebbero
    -0.67
    </b>
    -0.65
    <i>
    -0.64
    Beats
    -0.62
     it
    -0.62
    AdapterView
    -0.61
    Fla
    -0.59
     totales
    -0.59
    POSITIVE LOGITS
    MANY
    1.69
     MANY
    1.62
     many
    1.53
    many
    1.38
     Many
    1.30
    Many
    1.22
     muchos
    1.08
     Muitos
    1.04
    Viele
    1.04
    Muchos
    1.01
    Activations Density 0.102%

    No Known Activations