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. 16-GEMMASCOPE-RES-16K
    6. 6554
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and references related to programming and data structures

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

    followed by forms of "to be" or "to have."

    np_acts-logits-general · gemini-2.0-flash

    linking verbs after nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]='\
    -0.70
    etsa
    -0.63
    )]=
    -0.61
    ))));
    -0.58
    …)
    -0.56
    ]='
    -0.56
    clara
    -0.55
    WriteTagHelper
    -0.54
    ']}
    -0.53
    Enllaces
    -0.53
    POSITIVE LOGITS
     is
    0.94
     will
    0.87
     can
    0.83
     never
    0.82
     has
    0.82
     was
    0.80
     had
    0.77
     have
    0.76
     cannot
    0.76
     also
    0.76
    Activations Density 2.923%

    No Known Activations