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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 6050
    Prev
    Next
    INDEX
    Explanations

    numerical values and codes related to digital or technical variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     présidenti
    -0.55
    NameInMap
    -0.53
     préc
    -0.51
    jabat
    -0.50
    BufferException
    -0.47
     américains
    -0.47
     passés
    -0.47
    +#+#
    -0.46
    tahankan
    -0.46
     máme
    -0.45
    POSITIVE LOGITS
    ChildScrollView
    0.79
    terase
    0.72
    ngdoc
    0.70
    Спољашње
    0.70
     HasFactory
    0.63
    存于互联网档案馆
    0.60
    ----</
    0.59
     ExecuteAsync
    0.58
    iastical
    0.57
     يتيمه
    0.56
    Activations Density 1.138%

    No Known Activations