© 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. 17-GEMMASCOPE-RES-16K
    11. 12842
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions indicating reasoning or justification

    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
     vor
    -0.45
     d
    -0.43
    ものの
    -0.39
     noch
    -0.38
    ALM
    -0.37
     sinar
    -0.37
     als
    -0.35
     mit
    -0.35
    了
    -0.35
    notifier
    -0.35
    POSITIVE LOGITS
     itulah
    1.60
    這就是
    1.51
    这就是
    1.49
     thats
    1.37
     Именно
    1.37
     inilah
    1.35
    これが
    1.25
     Thats
    1.12
    それが
    1.09
    thats
    1.08
    Activations Density 0.250%

    No Known Activations