© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 5769
    Prev
    Next
    INDEX
    Explanations

    references to the word "many" or discussions involving numerosity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    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
    -0.69
    </b>
    -0.68
     FLA
    -0.66
     dovrebbero
    -0.64
    <i>
    -0.63
    Beats
    -0.62
    oz
    -0.61
     azzurro
    -0.60
    TargetApi
    -0.60
    axel
    -0.60
    POSITIVE LOGITS
    MANY
    1.44
     MANY
    1.43
     many
    1.25
    many
    1.12
     Many
    1.11
    Many
    0.97
     CreateTagHelper
    0.92
     muchos
    0.90
    Cuántos
    0.88
    Muchos
    0.87
    Activations Density 0.052%

    No Known Activations