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. 6738
    Prev
    Next
    INDEX
    Explanations

    conjunctions or connecting words in the text

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

    Code-related syntax and symbols

    np_acts-logits-general · gemini-2.0-flash

    numbers, surrounding context

    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
     Púb
    -0.53
     Here
    -0.47
     relatifs
    -0.46
    BagLayout
    -0.44
    پیوند
    -0.44
    guió
    -0.43
     riconoscimento
    -0.42
    WebControls
    -0.42
     affitto
    -0.41
     holds
    -0.41
    POSITIVE LOGITS
    =$?
    0.84
    存于互联网档案馆
    0.77
    istoitu
    0.73
    ++);
    0.72
    CppCodeGen
    0.71
    )_/¯
    0.67
     незавершена
    0.67
     /\.(
    0.67
    Personensuche
    0.66
    ++];
    0.66
    Activations Density 0.093%

    No Known Activations