© 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. 18-GEMMASCOPE-RES-16K
    11. 377
    Prev
    Next
    INDEX
    Explanations

    references to songs and musical elements

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

    "song" or "songs"

    np_acts-logits-general · gemini-2.0-flash

    song followed by descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.86
     CWE
    -0.82
    허
    -0.70
    contentLoaded
    -0.69
    nonatomic
    -0.67
     nonatomic
    -0.66
     setOpen
    -0.64
    PerformLayout
    -0.64
    adaptiveStyles
    -0.64
    yyah
    -0.62
    POSITIVE LOGITS
     songs
    1.35
     song
    1.25
     Song
    1.19
    Song
    1.17
     Songs
    1.16
     SONG
    1.16
    Songs
    1.13
    song
    1.11
    songs
    1.01
    SONG
    1.00
    Activations Density 0.116%

    No Known Activations