© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 4739
    Prev
    Next
    INDEX
    Explanations

    instances of perseverance and struggle in human experiences

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

    Tokens preceding forms of "manage"

    np_acts-logits-general · gemini-2.0-flash

    managing to do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endpush
    -0.52
     hini
    -0.50
    outSlope
    -0.50
    ANIEL
    -0.49
     Britton
    -0.49
    therosclerosis
    -0.48
    NotImplemented
    -0.48
    amenta
    -0.48
    BeginContext
    -0.47
    hamn
    -0.47
    POSITIVE LOGITS
     managed
    2.83
     manage
    2.59
     manages
    2.48
    managed
    2.38
     managing
    2.13
    manage
    2.06
     Managed
    2.06
    Managed
    2.05
     Manage
    1.90
    managing
    1.80
    Activations Density 0.624%

    No Known Activations