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. 18-GEMMASCOPE-RES-16K
    6. 830
    Prev
    Next
    INDEX
    Explanations

    requests for assistance or service

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

    Precedes "to" or expresses desire

    np_acts-logits-general · gemini-2.0-flash

    want to / derivative of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.70
    roek
    -0.58
     Roskov
    -0.58
     existir
    -0.55
    AnchorTagHelper
    -0.54
     först
    -0.54
     layui
    -0.53
    UnusedPrivate
    -0.51
    WebVitals
    -0.50
    ukkig
    -0.50
    POSITIVE LOGITS
     something
    0.73
     urgently
    0.71
     quick
    0.63
    PasswordEncoder
    0.60
    __":
    0.59
    Sharper
    0.58
    Something
    0.57
    хьтан
    0.57
     něco
    0.57
    something
    0.56
    Activations Density 0.177%

    No Known Activations