© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 9968
    Prev
    Next
    INDEX
    Explanations

    technical terms and quantitative measurements related to scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ProtoMessage
    -0.44
    fromnode
    -0.40
     useSelector
    -0.36
    WriteTagHelper
    -0.35
     LoginComponent
    -0.33
    chale
    -0.32
    redes
    -0.32
     viewDidLoad
    -0.32
    <em>
    -0.32
     Spinner
    -0.31
    POSITIVE LOGITS
    Personensuche
    0.73
     queſta
    0.51
    \{\\
    0.50
     мәкал
    0.50
    ariConfig
    0.50
    kuuta
    0.49
    StoryboardSegue
    0.48
     Référence
    0.46
     TextAppearance
    0.46
    __*/
    0.46
    Activations Density 1.258%

    No Known Activations