© 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. 23-GEMMASCOPE-RES-16K
    11. 1982
    Prev
    Next
    INDEX
    Explanations

    information related to timelines and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <i>
    -0.42
    <em>
    -0.40
    hira
    -0.37
    ]),
    -0.36
    <sub>
    -0.36
    тинки
    -0.35
    <b>
    -0.35
    <strong>
    -0.35
    <u>
    -0.35
      
    -0.35
    POSITIVE LOGITS
    Personensuche
    0.69
     resourceCulture
    0.59
     defaultstate
    0.52
    RTEE
    0.49
    windowFixed
    0.49
     invokingState
    0.48
     
    0.48
    NUMX
    0.46
    webElementXpaths
    0.45
     '\\;'
    0.45
    Activations Density 0.563%

    No Known Activations