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. 7326
    Prev
    Next
    INDEX
    Explanations

    elements related to specific protocols and guidelines in a research context

    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
    UrlResolution
    -0.67
    +#+#
    -0.65
    #+#
    -0.63
    UIControlState
    -0.61
     Efq
    -0.59
     useDispatch
    -0.58
    ---|---|
    -0.58
    ---*/
    -0.57
    withIdentifier
    -0.56
     pleaſure
    -0.56
    POSITIVE LOGITS
    ⓧ
    0.58
     Tell
    0.49
    تقاوى
    0.47
     &___
    0.43
     gross
    0.42
     ویکی‌پدی
    0.42
    matchCondition
    0.42
    protoimpl
    0.41
     TELL
    0.41
    getSystem
    0.41
    Activations Density 1.514%

    No Known Activations