© 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. 17-GEMMASCOPE-RES-16K
    6. 10420
    Prev
    Next
    INDEX
    Explanations

    references to similarity and comparison in contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //
    -0.45
    koi
    -0.43
     sekali
    -0.42
    eld
    -0.41
    都不是
    -0.40
    SetUp
    -0.40
    apa
    -0.37
     createState
    -0.37
    isse
    -0.37
    するには
    -0.37
    POSITIVE LOGITS
     similarly
    3.04
     same
    3.02
    same
    3.00
    Same
    2.88
     similar
    2.87
    Similarly
    2.82
     Similarly
    2.72
    similar
    2.69
     Same
    2.68
    Likewise
    2.45
    Activations Density 1.241%

    No Known Activations