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. 9-GEMMASCOPE-RES-16K
    6. 15286
    Prev
    Next
    INDEX
    Explanations

    elements related to structured data and programming functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.92
    AddTagHelper
    -0.78
    ########.
    -0.76
    ViewFeatures
    -0.74
    urably
    -0.72
    TestingModule
    -0.69
    adaptiveStyles
    -0.65
     الحره
    -0.64
    ContentAlignment
    -0.64
    brigens
    -0.63
    POSITIVE LOGITS
    DockStyle
    0.75
    event
    0.54
     reservados
    0.54
    NewGuid
    0.53
    getOutputStream
    0.51
    findpost
    0.50
     events
    0.48
     event
    0.48
    agot
    0.47
    atisk
    0.47
    Activations Density 0.019%

    No Known Activations