© 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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 6956
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and expressions related to statistical analysis and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISupport
    -0.73
    رشف
    -0.54
     Mgr
    -0.53
    ginfo
    -0.50
    ardige
    -0.50
    uxe
    -0.50
    OGND
    -0.49
    存于互联网档案馆
    -0.47
    isted
    -0.46
    ][:
    -0.46
    POSITIVE LOGITS
     فريبيس
    0.73
     GetEnumerator
    0.70
    ClientSize
    0.69
    的值
    0.65
    값
    0.65
     value
    0.64
     values
    0.63
    intios
    0.61
     ranging
    0.60
    值
    0.59
    Activations Density 1.576%

    No Known Activations