Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3485
    Prev
    Next
    INDEX
    Explanations

    various HTML and character encoding elements

    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
    ंदीखरीदारी
    -0.64
    ::~
    -0.54
    DebuggerNonUser
    -0.52
    terdam
    -0.51
    RoutingModule
    -0.51
     насељу
    -0.51
     createSprite
    -0.51
     रेटिंग
    -0.50
    windowFixed
    -0.50
    erialization
    -0.49
    POSITIVE LOGITS
     externi
    0.54
     '\\;'
    0.51
    endif
    0.48
    hexyl
    0.47
    ун
    0.46
    Reminds
    0.45
    LEADING
    0.44
    unek
    0.44
     ta
    0.44
    xff
    0.44
    Activations Density 0.186%

    No Known Activations