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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5879
    Prev
    Next
    INDEX
    Explanations

    references to notable alumni and educational institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cherchés
    -0.57
     चीज़ों
    -0.51
     الحره
    -0.47
    migrationBuilder
    -0.45
     bluzka
    -0.44
     itſelf
    -0.43
    Nuorodos
    -0.43
     kurtka
    -0.42
     _:
    -0.42
    ])).
    -0.42
    POSITIVE LOGITS
     alumni
    0.82
     alumnus
    0.75
     Alumni
    0.70
     graduates
    0.69
    alumni
    0.68
     graduating
    0.67
    Alumni
    0.66
     graduation
    0.64
     graduate
    0.63
     gradu
    0.63
    Activations Density 0.168%

    No Known Activations