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. 16-GEMMASCOPE-RES-16K
    6. 3
    Prev
    Next
    INDEX
    Explanations

    the presence of specific titles or identifiers

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

    Follows a period or is at the start of a line

    np_acts-logits-general · gemini-2.0-flash

    foreign words and growing

    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
    XDECREF
    -0.64
    ,:),
    -0.64
     विश्वसनीयता
    -0.63
    kloped
    -0.63
    >");
    
    -0.63
    TemporalType
    -0.63
     }}"></
    -0.62
    }>;
    -0.60
    DataPropertyName
    -0.60
    ();)
    -0.60
    POSITIVE LOGITS
     Италијани
    0.59
    Growing
    0.59
     Growing
    0.56
    Many
    0.54
     growing
    0.54
     Many
    0.53
    众
    0.51
    自从
    0.49
    Portail
    0.49
    growing
    0.48
    Activations Density 0.264%

    No Known Activations