© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8253
    Prev
    Next
    INDEX
    Explanations

    phrases indicating memory recall and questioning understanding of past events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Expressing memory or thought processes

    np_acts-logits-general · gemini-2.0-flash

    memory and recall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.67
     itſelf
    -0.66
    PerformLayout
    -0.64
     Reſ
    -0.64
     Inſ
    -0.64
    ſelf
    -0.63
     ſever
    -0.63
     '\\;'
    -0.63
     myſelf
    -0.62
     Monfieur
    -0.62
    POSITIVE LOGITS
     memory
    0.59
     recall
    0.59
     remembers
    0.54
     remember
    0.54
     remembering
    0.52
     somewhere
    0.52
     recollection
    0.50
     remembered
    0.50
     Recall
    0.50
     memor
    0.49
    Activations Density 0.238%

    No Known Activations