© 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. 3304
    Prev
    Next
    INDEX
    Explanations

    terms related to evaluation and assessment in various contexts

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

    Follows certain verbs (manage) or nouns (loan)

    np_acts-logits-general · gemini-2.0-flash

    manage loans and eyeglass frames

    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
    SourceChecksum
    -1.11
     propOrder
    -1.08
    __':
    
    -1.00
    TagMode
    -0.95
    kháu
    -0.92
    +#+#
    -0.91
    Autoritní
    -0.85
     snippetHide
    -0.83
    __":
    
    -0.82
     StatelessWidget
    -0.81
    POSITIVE LOGITS
     olmayan
    0.71
     itself
    0.64
     indeed
    0.60
     because
    0.57
    といっても
    0.56
     means
    0.55
     stesso
    0.53
    と言っても
    0.53
    どころ
    0.52
     yapan
    0.51
    Activations Density 0.697%

    No Known Activations