© 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. 18-GEMMASCOPE-RES-16K
    6. 14210
    Prev
    Next
    INDEX
    Explanations

    discussions around the effectiveness and potential of substitutes or alternatives in addressing environmental issues

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

    Followed by "do the same" or similar phrase

    np_acts-logits-general · gemini-2.0-flash

    similar and same

    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
    //
    -0.54
    хьтан
    -0.52
    都不是
    -0.47
     propOrder
    -0.46
    hoeddwyd
    -0.45
     通販
    -0.45
    colha
    -0.45
    sweise
    -0.45
     معرف
    -0.44
    PositiveButton
    -0.44
    POSITIVE LOGITS
     similar
    3.43
     similarly
    3.31
    similar
    3.15
    Similar
    2.97
     same
    2.94
    Similarly
    2.92
    same
    2.90
     Similar
    2.87
    Same
    2.87
     Similarly
    2.81
    Activations Density 1.807%

    No Known Activations