© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4344
    Prev
    Next
    INDEX
    Explanations

    links or prompts to additional content or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.65
    Portály
    -0.63
    كويكب
    -0.57
     препратки
    -0.56
    addContainerGap
    -0.51
     AssemblyCompany
    -0.51
    новништво
    -0.50
     незавершена
    -0.49
    erdings
    -0.48
     Signalez
    -0.48
    POSITIVE LOGITS
    Autowired
    0.82
    come
    0.57
    Come
    0.54
     Come
    0.50
     come
    0.46
     cash
    0.44
    ;&
    0.42
    ########.
    0.42
     pleaſure
    0.40
    cash
    0.40
    Activations Density 0.093%

    No Known Activations