Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1018
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing clinical significance and relevance to public health

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

    relevance or importance

    np_acts-logits-general · gemini-2.0-flash

    importance and implications

    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
     älskar
    -0.59
     rígida
    -0.57
    }}/>
    -0.52
    MessageTagHelper
    -0.51
    StoryboardSegue
    -0.49
    AndEndTag
    -0.49
    цездатний
    -0.48
     reposer
    -0.48
     rígido
    -0.48
     समीक्षाएं
    -0.47
    POSITIVE LOGITS
     relevance
    1.97
     importance
    1.71
     significance
    1.69
     Relevance
    1.67
    Relevance
    1.54
     relevant
    1.50
     Importance
    1.46
    relevance
    1.45
    Importance
    1.43
     Significance
    1.43
    Activations Density 0.729%

    No Known Activations