© 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. 37-GEMMASCOPE-RES-16K
    11. 5673
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and personal memories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.59
    ScopeManager
    -0.58
    posedge
    -0.56
    sscanf
    -0.49
    COUVER
    -0.49
     nonUne
    -0.45
    RegressionTest
    -0.45
    TagHelper
    -0.44
    engertian
    -0.44
    ſelf
    -0.43
    POSITIVE LOGITS
     remember
    0.71
     recall
    0.70
     vividly
    0.63
     recalls
    0.61
     remembers
    0.57
     later
    0.57
    今でも
    0.54
     think
    0.52
    vivid
    0.51
     believe
    0.49
    Activations Density 0.365%

    No Known Activations