© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 5047
    Prev
    Next
    INDEX
    Explanations

    negative evaluations and critiques of statements or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HandlerContext
    -0.46
     lenker
    -0.40
     protoimpl
    -0.37
    endpush
    -0.36
    ahme
    -0.35
    NameInMap
    -0.35
     <<<<<<<<<<<<<<
    -0.35
     voire
    -0.34
    enumi
    -0.34
    initializeApp
    -0.34
    POSITIVE LOGITS
     obviously
    3.00
    obviously
    2.83
    Obviously
    2.50
     oczywiście
    2.48
     Obviously
    2.48
     ovviamente
    2.47
     natürlich
    2.42
     obviamente
    2.41
     évidemment
    2.36
    當然
    2.33
    Activations Density 1.035%

    No Known Activations