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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122883
    Prev
    Next
    INDEX
    Explanations

    terms related to community services and support structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     HttpNotFound
    -0.48
    resizingMask
    -0.39
     []:
    -0.39
    zzleHttp
    -0.39
     doInBackground
    -0.38
    roughts
    -0.37
     étrangère
    -0.36
    Kariera
    -0.36
    Rüyada
    -0.35
    Билгалдахарш
    -0.35
    POSITIVE LOGITS
     program
    0.63
     Counseling
    0.59
     pediat
    0.57
     Program
    0.57
     counseling
    0.57
     clinic
    0.56
    Programs
    0.54
     therapist
    0.54
     Programs
    0.54
     therap
    0.53
    Activations Density 0.046%

    No Known Activations