Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3046
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic or organizational classifications and statistical data metrics

    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
    InjectAttribute
    -1.08
     незавершена
    -1.07
    曖昧さ回避
    -1.07
    出版年
    -1.03
     nakalista
    -1.03
    IUrlHelper
    -1.02
    webElementXpaths
    -1.01
    $_['
    -1.00
    تقاوى
    -1.00
    ########.
    -0.97
    POSITIVE LOGITS
    ↵↵
    0.53
    N
    0.52
    U
    0.51
    u
    0.51
    k
    0.47
    m
    0.47
    j
    0.47
    um
    0.45
    c
    0.45
    C
    0.44
    Activations Density 0.349%

    No Known Activations