© 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. 9-GEMMASCOPE-RES-16K
    6. 7674
    Prev
    Next
    INDEX
    Explanations

    JavaScript or related programming constructs that utilize observables and dependency injection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AxisAlignment
    -0.95
    aarrggbb
    -0.83
     []:
    -0.83
    __':
    -0.79
    StoryboardSegue
    -0.79
     '\\;'
    -0.79
     noqa
    -0.78
     EdgeInsets
    -0.77
    nocache
    -0.77
    +#+#
    -0.76
    POSITIVE LOGITS
     useState
    2.62
    useState
    2.28
     useEffect
    1.06
    useEffect
    0.86
     useDispatch
    0.57
     useRef
    0.57
     useCallback
    0.53
     thận
    0.52
    Становништво
    0.50
    Obrázky
    0.50
    Activations Density 0.001%

    No Known Activations