Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 681
    Prev
    Next
    INDEX
    Explanations

    phrases that express distance or extent

    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
     nakalista
    -0.73
     AspNetCore
    -0.69
    complexContent
    -0.57
    ATTN
    -0.54
    #+#
    -0.52
    кновен
    -0.52
    xae
    -0.51
     ioutil
    -0.51
     Bakar
    -0.51
    endpush
    -0.50
    POSITIVE LOGITS
     distance
    1.33
     distances
    1.29
     Distance
    1.16
     Distances
    1.15
    distance
    1.14
     DISTANCE
    1.11
    DISTANCE
    1.10
    Distance
    1.07
     distancia
    1.03
    distances
    1.00
    Activations Density 0.194%

    No Known Activations