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. 23-GEMMASCOPE-RES-131K
    6. 105
    Prev
    Next
    INDEX
    Explanations

    references to parent-child relationships and parental involvement

    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_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.58
    SharedDtor
    -0.49
     BorderRadius
    -0.49
    省市镇
    -0.45
    vator
    -0.45
    copg
    -0.45
    scribers
    -0.44
    weds
    -0.44
     Couple
    -0.43
     pegat
    -0.43
    POSITIVE LOGITS
     father
    0.55
     bonding
    0.53
     bond
    0.51
    親子
    0.50
    father
    0.47
     BOND
    0.47
    父子
    0.46
     daddy
    0.42
     grandson
    0.42
     dad
    0.41
    Activations Density 0.042%

    No Known Activations