© 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. 14-GEMMASCOPE-RES-16K
    6. 7883
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to scientific processes and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    原始内容存档于
    -0.58
     Infórmanos
    -0.58
    utnik
    -0.52
    AccessorTable
    -0.50
    ]")]
    -0.48
    новништво
    -0.48
    webElementXpaths
    -0.47
    complexContent
    -0.47
     للمعارف
    -0.47
    ThroughAttribute
    -0.46
    POSITIVE LOGITS
     convert
    0.55
     thành
    0.55
     Roskov
    0.55
    MenuInflater
    0.54
    ymal
    0.54
    EndInit
    0.54
     ↔
    0.53
     translate
    0.53
    ANDUM
    0.53
     into
    0.52
    Activations Density 0.666%

    No Known Activations