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. 12-GEMMASCOPE-RES-16K
    6. 15961
    Prev
    Next
    INDEX
    Explanations

    references to various medical conditions and their impacts

    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
    rø
    -0.58
     ervoor
    -0.58
     repairs
    -0.53
    GenerationType
    -0.51
     Directions
    -0.51
     directions
    -0.50
    leč
    -0.48
     so
    -0.48
    (?:
    -0.47
    OpenHelper
    -0.47
    POSITIVE LOGITS
     Roskov
    0.79
     protoimpl
    0.77
     שוליים
    0.68
    oredCriteria
    0.66
     Efq
    0.64
    Enllaces
    0.61
    parsedMessage
    0.61
    .........
    0.60
     myſelf
    0.59
     Theſe
    0.57
    Activations Density 0.702%

    No Known Activations