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. 12756
    Prev
    Next
    INDEX
    Explanations

    descriptions of characters or entities exhibiting specific attributes or qualities

    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
     OFDb
    -0.65
     ComVisible
    -0.61
    Хьажоргаш
    -0.59
    sizeCache
    -0.53
    rouvez
    -0.52
    Personendaten
    -0.52
     ويكيپيديا
    -0.51
     contextLoads
    -0.51
     Meksiku
    -0.51
     ICF
    -0.49
    POSITIVE LOGITS
     متعلقه
    0.66
    TRIBUTION
    0.65
    ]._
    0.65
     lombok
    0.63
    بوابة
    0.61
    |}{}
    0.60
     Rugg
    0.60
    addGap
    0.60
    ghu
    0.59
    hien
    0.58
    Activations Density 0.542%

    No Known Activations