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. 21773
    Prev
    Next
    INDEX
    Explanations

    references to aquariums and marine environments

    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
     يتيمه
    -0.68
    AddTagHelper
    -0.65
    SequentialGroup
    -0.64
     estekak
    -0.59
    SourceChecksum
    -0.57
     AssemblyCompany
    -0.53
    homonymie
    -0.53
    GOTREF
    -0.51
    hilangan
    -0.49
    Personendaten
    -0.49
    POSITIVE LOGITS
     aquarium
    0.61
     Aquarium
    0.50
    aquarium
    0.44
     terrarium
    0.41
     cage
    0.37
     uLocal
    0.36
    帖最后由
    0.36
    urtstag
    0.35
     glass
    0.34
     Navidad
    0.34
    Activations Density 0.005%

    No Known Activations