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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 45525
    Prev
    Next
    INDEX
    Explanations

    contexts involving measurements and assessments of size, weight, and capabilities of objects or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageOf
    -0.48
     GenerationType
    -0.47
     onCreateView
    -0.45
    帖最后由
    -0.39
    ForRow
    -0.38
    Заключение
    -0.38
    geddon
    -0.38
     uLocal
    -0.38
    ReusableCell
    -0.38
    XMLSchema
    -0.36
    POSITIVE LOGITS
     ujednoznacz
    0.61
    verwijspagina
    0.48
    鰭
    0.47
    EDEFAULT
    0.46
    httphttps
    0.46
     Económica
    0.46
    iyle
    0.44
     CreateTagHelper
    0.43
     svårt
    0.42
    istoitu
    0.42
    Activations Density 0.033%

    No Known Activations