© 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. 1550
    Prev
    Next
    INDEX
    Explanations

    references to success and achievements in various 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
     AssemblyTitle
    -0.73
     bershka
    -0.67
    endforeach
    -0.64
    ientí
    -0.61
     protoimpl
    -0.61
     getItemId
    -0.60
    viewDidLoad
    -0.60
    </tfoot>
    -0.57
     GIPHY
    -0.55
    MethodManager
    -0.55
    POSITIVE LOGITS
     success
    1.91
     successful
    1.67
     succès
    1.66
     Success
    1.66
    success
    1.62
    Success
    1.57
     SUCCESS
    1.55
     éxito
    1.46
     successes
    1.43
     sucesso
    1.39
    Activations Density 0.259%

    No Known Activations