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. 2-GEMMASCOPE-RES-16K
    6. 2116
    Prev
    Next
    INDEX
    Explanations

    greetings or informal salutations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ^^^^^^^^
    -0.70
    تفصیلات
    -0.65
    多い
    -0.61
    orited
    -0.59
    Cordialement
    -0.59
    ワイイ
    -0.58
    uolo
    -0.57
    bleau
    -0.57
    omány
    -0.56
    piac
    -0.56
    POSITIVE LOGITS
    Hey
    2.13
     Hey
    2.07
     hey
    1.74
    hey
    1.63
     HEY
    1.48
    Hello
    1.47
    HEY
    1.39
     Hello
    1.37
    Dear
    1.22
    Heya
    1.14
    Activations Density 0.028%

    No Known Activations