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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 475
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals named Steve or Stephen, particularly in a cultural or media context

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

    references to notable figures, particularly those named Steve or Stephen

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.55
    LEncoder
    -0.52
    NewGuid
    -0.51
    saraba
    -0.46
    InjectMocks
    -0.46
     доступа
    -0.46
     ngang
    -0.46
    ButtonStyle
    -0.44
     صوتيه
    -0.44
    inelli
    -0.44
    POSITIVE LOGITS
    hoeddwyd
    0.69
     AssemblyCulture
    0.66
     Voulez
    0.58
    $_['
    0.57
    webElementXpaths
    0.53
    soort
    0.51
    تقاوى
    0.50
    MethodManager
    0.50
     CURIAM
    0.49
    IBarButtonItem
    0.49
    Activations Density 0.365%

    No Known Activations