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. 24-GEMMASCOPE-RES-16K
    6. 8213
    Prev
    Next
    INDEX
    Explanations

    elements related to software configuration settings and user interface options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Options or actions to choose/select

    np_acts-logits-general · gemini-2.0-flash

    custom options and settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxDecoration
    -0.61
    \{\\
    -0.60
     ligiloj
    -0.59
    ंदीखरीदारी
    -0.56
    LookAnd
    -0.56
    initializeApp
    -0.55
    Portale
    -0.54
     getVersion
    -0.53
     intptr
    -0.52
    abstractmethod
    -0.52
    POSITIVE LOGITS
     custom
    0.85
     Custom
    0.83
     predefined
    0.74
     preset
    0.72
    custom
    0.71
    ustom
    0.70
    Custom
    0.70
     specify
    0.68
     Specify
    0.67
     Choose
    0.67
    Activations Density 0.409%

    No Known Activations