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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15700
    Prev
    Next
    INDEX
    Explanations

    elements related to music track information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ir
    -0.47
     rayures
    -0.47
    idem
    -0.46
     cuantos
    -0.46
     المرجع
    -0.45
    acu
    -0.45
    ult
    -0.44
    alang
    -0.44
    insch
    -0.44
    cef
    -0.42
    POSITIVE LOGITS
    ImageContext
    1.06
    ReusableCell
    1.01
    JspWriter
    0.96
    __*/
    0.90
    Parcelize
    0.87
    tagHelperRunner
    0.86
    StoryboardSegue
    0.84
     للاسماء
    0.84
    principalColumn
    0.78
    Искәрмәләр
    0.78
    Activations Density 0.087%

    No Known Activations