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. 16-GEMMASCOPE-RES-16K
    6. 122
    Prev
    Next
    INDEX
    Explanations

    specific geographic locations and spatial relationships

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

    a location

    np_acts-logits-general · gemini-2.0-flash

    spatial prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Diweddarwch
    -0.54
     referrerpolicy
    -0.46
     presence
    -0.42
     setuptools
    -0.42
    κτηρισ
    -0.42
    NOPQRST
    -0.41
    presence
    -0.41
    {?>
    -0.40
    Externí
    -0.40
     tilbake
    -0.40
    POSITIVE LOGITS
    ]--;
    0.79
     resourceCulture
    0.69
    TagMode
    0.68
    IMPORTED
    0.66
    principalTable
    0.65
    __':
    0.65
    CodedInputStream
    0.65
    FontOfSize
    0.64
    MIDDLEWARE
    0.62
     Roskov
    0.61
    Activations Density 0.177%

    No Known Activations