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. 15-GEMMASCOPE-RES-16K
    6. 1778
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and references to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Diſ
    -1.21
     houſe
    -1.20
     Theſe
    -1.20
    ſelf
    -1.16
     becauſe
    -1.15
     itſelf
    -1.15
     myſelf
    -1.12
     Houſe
    -1.10
     Eſ
    -1.09
     ―――――
    -1.09
    POSITIVE LOGITS
     Von
    0.93
     von
    0.90
    Von
    0.82
     Steph
    0.76
    Steph
    0.74
    machus
    0.72
     Ste
    0.71
     Stephens
    0.69
     degré
    0.67
    ccc
    0.67
    Activations Density 0.514%

    No Known Activations