© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28400
    Prev
    Next
    INDEX
    Explanations

    alphanumeric identifiers or codes relevant to user permissions

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

    mathematical notation

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Ouvrez
    -0.64
    nodoc
    -0.63
    NullCheck
    -0.63
     ſon
    -0.62
    MessageOf
    -0.61
     >=",
    -0.58
     zeroes
    -0.58
    nosaurus
    -0.58
     zeros
    -0.57
     Commencez
    -0.57
    POSITIVE LOGITS
    strick
    0.52
     bed
    0.49
    GenerationType
    0.49
     Austausch
    0.47
     JComboBox
    0.47
     Lehr
    0.46
     exchange
    0.46
     lenker
    0.46
     transfert
    0.45
    }]
    0.44
    Activations Density 0.052%

    No Known Activations