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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1600
    Prev
    Next
    INDEX
    Explanations

    references to music albums and bands

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

    Metal, punk, or hardcore bands

    np_acts-logits-general · gemini-2.0-flash

    music bands and rock genres

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.61
     للاسماء
    -0.59
     TextAppearance
    -0.56
    GEBURTS
    -0.56
     للمعارف
    -0.54
    LEncoder
    -0.53
     ivelany
    -0.53
     CreateTagHelper
    -0.52
    ConstraintMaker
    -0.52
    MockBean
    -0.52
    POSITIVE LOGITS
     band
    0.40
     bands
    0.39
     fucking
    0.38
     bandas
    0.38
     fuckin
    0.36
     thrash
    0.36
     Band
    0.34
    期刊论文
    0.34
    ituary
    0.33
     Fucking
    0.33
    Activations Density 0.085%

    No Known Activations