© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7228
    Prev
    Next
    INDEX
    Explanations

    elements related to data structures, XML schemas, and attributes within data fields

    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
    findpost
    -0.66
     betweenstory
    -0.64
    OGND
    -0.58
     Roskov
    -0.56
     procéder
    -0.53
     (
    -0.52
    échal
    -0.52
    AutoScaleMode
    -0.51
    +#+#
    -0.50
    onora
    -0.49
    POSITIVE LOGITS
    endphp
    1.01
     BoxDecoration
    0.81
    AnimationsModule
    0.75
    TemporalType
    0.73
    MethodManager
    0.73
    </tfoot>
    0.71
    存于互联网档案馆
    0.70
    Παραπομπές
    0.70
     isKindOfClass
    0.67
     IndexPath
    0.66
    Activations Density 0.111%

    No Known Activations