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

    Neuronpedia

    Jacobian LensNEW
    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. 4893
    Prev
    Next
    INDEX
    Explanations

    instances of the word "recover" and its derivatives, indicating a focus on recovery or restitution themes

    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
    RegistryLite
    -0.50
     Edu
    -0.47
    modelBuilder
    -0.47
    wikidata
    -0.46
    ########.
    -0.45
    fjspx
    -0.45
    Edu
    -0.44
    modore
    -0.44
    WriteBarrier
    -0.44
    bour
    -0.43
    POSITIVE LOGITS
     recovered
    0.71
     recover
    0.71
     recovers
    0.68
     recovering
    0.64
    recovered
    0.64
     students
    0.60
    recover
    0.60
    的学生
    0.56
    students
    0.56
    recovery
    0.56
    Activations Density 0.087%

    No Known Activations