© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 1490
    Prev
    Next
    INDEX
    Explanations

    HTML tags and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createState
    -0.55
    SequentialGroup
    -0.54
     <<<<<<<<<<<<<<
    -0.51
    colhead
    -0.50
    setContentView
    -0.49
    akyti
    -0.47
    ngOnInit
    -0.47
    ArgumentParser
    -0.46
     VIAF
    -0.46
    gatsby
    -0.46
    POSITIVE LOGITS
     Италијани
    0.84
     defaultstate
    0.83
     يتيمه
    0.73
     ویکی‌پدی
    0.71
     виправивши
    0.69
    uegos
    0.68
    vician
    0.67
    CloseOperation
    0.67
    følgelig
    0.66
    couple
    0.65
    Activations Density 0.181%

    No Known Activations