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. 5200
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate relationships or connections between individuals and groups

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

    "with" followed by a personality trait

    np_acts-logits-general · gemini-2.0-flash

    attributes following with

    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
     defaultstate
    -0.84
    Хьажоргаш
    -0.78
    parsedMessage
    -0.71
     vôtre
    -0.70
     définiti
    -0.68
     userSchema
    -0.66
     мәкал
    -0.65
    зулта
    -0.65
    djangoproject
    -0.65
    jalá
    -0.65
    POSITIVE LOGITS
     ambitions
    0.69
     aspirations
    0.65
     passion
    0.63
     experience
    0.62
     interests
    0.61
     knowledge
    0.61
     strong
    0.59
     skills
    0.57
     no
    0.56
     ambition
    0.56
    Activations Density 0.411%

    No Known Activations