Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 5288
    Prev
    Next
    INDEX
    Explanations

    references to parental relationships and family dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding familial relationships or connections

    np_acts-logits-general · gemini-2.0-flash

    family and friends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    춰
    -0.48
    netbeans
    -0.47
    enumi
    -0.45
    Bibliograf
    -0.44
    SceneManagement
    -0.44
    逅
    -0.43
     Gazetteer
    -0.43
     kaarangay
    -0.42
    췄
    -0.42
    rafa
    -0.42
    POSITIVE LOGITS
     family
    1.27
    family
    1.18
     FAMILY
    1.10
    Family
    1.04
     Family
    1.01
    FAMILY
    0.98
     familie
    0.96
     famiglia
    0.92
     familien
    0.92
     familia
    0.90
    Activations Density 0.133%

    No Known Activations