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. 24-GEMMASCOPE-RES-16K
    6. 13903
    Prev
    Next
    INDEX
    Explanations

    attributes related to a person's versatility and adaptability in various situations, particularly in creative and professional contexts

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

    before "is," "was," or "are."

    np_acts-logits-general · gemini-2.0-flash

    earned qualities and benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FieldBuilder
    -0.59
    脚注の使い方
    -0.57
    SerializedSize
    -0.55
    httphttps
    -0.55
    InstanceState
    -0.52
    "/></
    -0.52
    scriptId
    -0.51
    rawtypes
    -0.51
    hdys
    -0.49
     aktivitet
    -0.48
    POSITIVE LOGITS
     earned
    0.87
     ende
    0.76
     earns
    0.71
     earning
    0.70
     earn
    0.69
    earned
    0.67
     enabled
    0.66
     extends
    0.64
     prompted
    0.63
     enables
    0.63
    Activations Density 0.299%

    No Known Activations