© 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-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 3019
    Prev
    Next
    INDEX
    Explanations

    instances of the word "desired" and its variations, indicating a focus on preferences or specific conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ben
    -0.46
     Per
    -0.46
     Se
    -0.45
    -
    -0.44
     
    -0.43
     a
    -0.43
    eson
    -0.42
    ,
    -0.42
     Independent
    -0.42
    ↵
    -0.42
    POSITIVE LOGITS
     Theſe
    0.72
     Monfieur
    0.68
     plufieurs
    0.68
     increí
    0.66
     Houſe
    0.66
     houſe
    0.65
     pérd
    0.65
     desmotivaciones
    0.62
     ainfi
    0.61
    Jeografia
    0.61
    Activations Density 0.325%

    No Known Activations