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

    Neuronpedia

    APICircuit 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. 2299
    Prev
    Next
    INDEX
    Explanations

    Arabic names or titles, particularly those with the prefix "al-"

    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
     autorytatywna
    -0.63
     Philli
    -0.50
    IRIT
    -0.46
    kład
    -0.46
     me
    -0.44
    LineNumber
    -0.43
     Autres
    -0.42
    Campe
    -0.42
     South
    -0.42
     Two
    -0.42
    POSITIVE LOGITS
     Италијани
    0.67
    ThroughAttribute
    0.67
    SerializedSize
    0.62
    mybatisplus
    0.62
    ***********/
    0.61
     Photocase
    0.61
    LookAnd
    0.60
    .*")]
    0.60
    ErrorListener
    0.59
    ritsar
    0.59
    Activations Density 0.115%

    No Known Activations