© 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. 2-GEMMASCOPE-RES-16K
    6. 13526
    Prev
    Next
    INDEX
    Explanations

    references to attributes or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.73
    OGND
    -0.40
    ResumeLayout
    -0.39
    Бахар
    -0.37
    ChildScrollView
    -0.36
    États
    -0.36
    Халык
    -0.35
     Hobson
    -0.35
    исленность
    -0.35
     Crocker
    -0.34
    POSITIVE LOGITS
    attr
    0.67
     merchant
    0.66
     Merchant
    0.64
    ator
    0.62
     grace
    0.60
     Infinity
    0.59
     onion
    0.59
    者
    0.59
     Grace
    0.58
     MERCHANT
    0.58
    Activations Density 0.397%

    No Known Activations