© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 14873
    Prev
    Next
    INDEX
    Explanations

    the word "up" in various contexts

    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
    Hör
    -0.68
     tagName
    -0.68
     Aner
    -0.67
     endfor
    -0.66
     Exc
    -0.65
    posedge
    -0.65
     '+':
    -0.65
     brightened
    -0.65
    setVerticalGroup
    -0.64
    greenrobot
    -0.64
    POSITIVE LOGITS
     итоге
    0.75
     eventually
    0.67
     become
    0.67
    interopRequire
    0.63
     actually
    0.61
     getting
    0.60
     Wirklichkeit
    0.59
    ویت
    0.58
     becoming
    0.58
     ultimately
    0.57
    Activations Density 0.131%

    No Known Activations