© 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. 39-GEMMASCOPE-RES-16K
    11. 720
    Prev
    Next
    INDEX
    Explanations

    technical specifications and configuration-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.60
     snippetHide
    -0.52
     Administrativna
    -0.51
    BeginInit
    -0.51
    wiſe
    -0.51
    AddTagHelper
    -0.49
     transférez
    -0.49
    RegressionTest
    -0.48
    MLLoader
    -0.46
    ConstraintMaker
    -0.46
    POSITIVE LOGITS
     default
    3.89
    default
    3.39
     Default
    3.13
    Default
    2.98
     defaults
    2.77
     defaulted
    2.61
    默认
    2.61
     DEFAULT
    2.59
    DEFAULT
    2.47
    デフォ
    2.45
    Activations Density 0.712%

    No Known Activations