© 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. 7919
    Prev
    Next
    INDEX
    Explanations

    terms related to research, compliance, and specific industries or sectors

    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
    BeginContext
    -0.57
     religieuses
    -0.57
    NameInMap
    -0.57
    ⓧ
    -0.47
     '\\;'
    -0.46
    rungsseite
    -0.46
    ]--;
    -0.46
    мость
    -0.45
     rossa
    -0.45
    meck
    -0.44
    POSITIVE LOGITS
    Демографія
    0.66
    ministrazione
    0.62
    soever
    0.60
     arena
    0.60
    BorderFactory
    0.60
     maail
    0.60
     realm
    0.60
    ValueGeneration
    0.59
    nteral
    0.59
     regime
    0.58
    Activations Density 0.527%

    No Known Activations