© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 8307
    Prev
    Next
    INDEX
    Explanations

    the mention of specific locations and their associated land uses, particularly related to Shaoyang

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.81
     Aires
    -0.68
    mtable
    -0.67
    otho
    -0.66
    ıdır
    -0.66
     Fro
    -0.65
     Meteor
    -0.64
    ufficio
    -0.64
     Murch
    -0.64
    +#+
    -0.64
    POSITIVE LOGITS
    Sha
    1.23
     Sha
    1.21
     Shapiro
    1.17
    sha
    1.16
     Shasta
    1.10
     Shaffer
    1.09
     sha
    0.99
     SHA
    0.98
    Shady
    0.94
     shading
    0.93
    Activations Density 0.268%

    No Known Activations