Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7611
    Prev
    Next
    INDEX
    Explanations

    elements related to nostalgia 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 @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.40
     updates
    -0.36
     optim
    -0.36
    updat
    -0.36
     update
    -0.36
     Update
    -0.35
     Updates
    -0.34
    ampunk
    -0.34
    SeekBar
    -0.34
     updating
    -0.34
    POSITIVE LOGITS
     recollections
    0.89
     recalled
    0.89
     reminis
    0.85
     memories
    0.85
     recollection
    0.84
     remembered
    0.82
     herinner
    0.82
     remembers
    0.80
     вспомина
    0.79
     memory
    0.77
    Activations Density 0.750%

    No Known Activations