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. 15-GEMMASCOPE-RES-16K
    6. 8566
    Prev
    Next
    INDEX
    Explanations

    references to cultural elements and characteristics of places and people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '];?>
    -0.72
    ']?>
    -0.72
    ())));
    -0.69
    ']));
    -0.67
    '].'
    -0.66
    '],'
    -0.64
    ","");
    -0.62
    '].
    -0.61
    "].
    -0.61
    "]').
    -0.60
    POSITIVE LOGITS
     CreateTagHelper
    0.94
    IntoConstraints
    0.84
     ProtoMessage
    0.84
    AndEndTag
    0.82
     Мексичка
    0.77
    دانشنامهٔ
    0.76
    ConstraintMaker
    0.76
    StoryboardSegue
    0.76
     kasarigan
    0.75
     calendriers
    0.74
    Activations Density 0.362%

    No Known Activations