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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7874
    Prev
    Next
    INDEX
    Explanations

    elements related to teaching and empowerment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.49
    bootstrapcdn
    -0.47
    RoutingModule
    -0.44
    HomeAsUp
    -0.44
     Bioaccumulative
    -0.44
     (§
    -0.43
    AccessorTable
    -0.42
     groupBox
    -0.42
    ༘
    -0.42
     proceder
    -0.40
    POSITIVE LOGITS
     positivity
    0.46
     herkes
    0.43
     connections
    0.42
    ंदीखरीदारी
    0.40
     awareness
    0.40
     possibilities
    0.40
     sustainable
    0.39
     reciprocity
    0.38
     intimacy
    0.38
    connect
    0.38
    Activations Density 0.246%

    No Known Activations