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. 18-GEMMASCOPE-RES-16K
    6. 3183
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations and states

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

    US states and countries

    np_acts-logits-general · gemini-2.0-flash

    US state names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.66
    XmlAccessType
    -0.65
    addContainerGap
    -0.63
    pellier
    -0.53
    мно
    -0.53
    didSet
    -0.52
    mberto
    -0.52
     поведения
    -0.51
    [](
    -0.51
    herjee
    -0.50
    POSITIVE LOGITS
    tvguidetime
    0.77
     OFDb
    0.69
     AllAfrica
    0.63
     AppColors
    0.62
    \{\\
    0.60
    xase
    0.60
     ujednoznacz
    0.56
    StateManager
    0.56
    RTEE
    0.54
    <()>
    0.54
    Activations Density 0.470%

    No Known Activations