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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13123
    Prev
    Next
    INDEX
    Explanations

    instances of the term "ju" or variations thereof, indicating a focus on musical jukeboxes or related concepts

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

    "Ju" followed by a lowercase letter

    np_acts-logits-general · gemini-2.0-flash

    jukebox or jurists

    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
    side
    -0.47
     EClass
    -0.46
    UnknownFieldSet
    -0.43
    roon
    -0.41
     прово
    -0.40
    unregister
    -0.39
    outer
    -0.39
    érale
    -0.39
    ough
    -0.38
     double
    -0.38
    POSITIVE LOGITS
    enumi
    0.91
    twimg
    0.83
     Италијани
    0.72
    httphttps
    0.71
     Percussion
    0.69
    __':
    0.69
     NgModule
    0.68
     onCancelled
    0.68
    =$?
    0.65
     betweenstory
    0.65
    Activations Density 0.141%

    No Known Activations