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. 21-GEMMASCOPE-RES-16K
    6. 2078
    Prev
    Next
    INDEX
    Explanations

    entities related to journalism and professional roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    Such
    -0.49
     Such
    -0.48
    rinos
    -0.44
     sola
    -0.44
     slik
    -0.43
    rendo
    -0.43
    ţion
    -0.42
    这样的
    -0.42
     unattended
    -0.42
    AntiForgeryToken
    -0.42
    POSITIVE LOGITS
     known
    1.16
     founded
    1.12
     specializing
    1.07
     specialising
    1.02
     headquartered
    1.00
     born
    0.98
     originally
    0.98
     located
    0.94
    known
    0.91
     formerly
    0.91
    Activations Density 0.356%

    No Known Activations