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. 25-GEMMASCOPE-RES-16K
    6. 7815
    Prev
    Next
    INDEX
    Explanations

    code-related references, particularly in the context of managing UI tabs and event handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Blythe
    -0.60
     Marley
    -0.57
    Bly
    -0.51
    트
    -0.49
    BooleanField
    -0.48
    titut
    -0.48
     Bertha
    -0.48
     Harry
    -0.48
    ServletRequest
    -0.48
     Walmart
    -0.48
    POSITIVE LOGITS
     Ta
    2.49
     Tab
    2.29
    Ta
    2.27
    Tab
    2.17
     ta
    2.16
     tab
    2.11
     TA
    2.11
    ta
    1.95
    tab
    1.94
     TAB
    1.92
    Activations Density 0.382%

    No Known Activations