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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 77047
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of strengthening relationships or connections

    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
     actionTypes
    -0.56
    LookAnd
    -0.55
     viewType
    -0.52
    CPtr
    -0.52
    \{\\
    -0.52
     ReactDOM
    -0.51
    exitRule
    -0.49
     تعدى
    -0.49
     []:
    -0.49
    principalColumn
    -0.48
    POSITIVE LOGITS
    Strengthen
    1.20
     strengthening
    1.20
    strengthen
    1.20
     Strengthening
    1.16
     strengthen
    1.14
     Strengthen
    1.07
     strengthened
    1.02
     strengthens
    1.00
    strong
    0.91
     renforcer
    0.91
    Activations Density 0.010%

    No Known Activations