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. 5212
    Prev
    Next
    INDEX
    Explanations

    information related to accommodations and facilities

    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
     Anſ
    -1.25
     Theſe
    -1.22
     itſelf
    -1.19
     Houſe
    -1.14
     myſelf
    -1.10
     doubtnut
    -1.10
     pleaſure
    -1.09
     Diſ
    -1.08
    ſelf
    -1.08
     Majefty
    -1.08
    POSITIVE LOGITS
     /
    0.71
     realised
    0.68
    <eos>
    0.67
     -
    0.65
     :
    0.62
     +
    0.61
     тё
    0.60
     |
    0.59
     €
    0.57
     analysed
    0.56
    Activations Density 0.273%

    No Known Activations