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. 1080
    Prev
    Next
    INDEX
    Explanations

    questions related to decision-making and options in various contexts

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

    Follows punctuation mark or symbol

    np_acts-logits-general · gemini-2.0-flash

    . followed by new sentences

    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
    englanniksi
    -0.57
     contd
    -0.54
    )}.
    -0.54
     Ferner
    -0.51
    ']}
    -0.50
     verder
    -0.49
    :✨
    -0.49
    :")
    -0.49
    istoitu
    -0.49
    ']).
    -0.48
    POSITIVE LOGITS
    ureusement
    0.77
     today
    0.76
    httphttps
    0.76
    そこで
    0.73
    Introducing
    0.72
    近日
    0.71
    Enter
    0.68
     voici
    0.67
     Introducing
    0.67
    exitRule
    0.67
    Activations Density 0.252%

    No Known Activations