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
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 4304
    Prev
    Next
    INDEX
    Explanations

    instances and mentions of being alone or in solitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataAnnotations
    -0.40
    Courtesy
    -0.38
    courtesy
    -0.36
     hulle
    -0.36
    Scopes
    -0.36
    hamshire
    -0.35
    テンツ
    -0.35
     Courtesy
    -0.35
    大家好
    -0.35
    Fizz
    -0.34
    POSITIVE LOGITS
     alone
    3.47
    alone
    3.11
     Alone
    3.03
     ALONE
    2.88
    Alone
    2.77
     allein
    2.28
     alene
    2.20
     alleine
    2.17
     solo
    2.13
     lone
    2.05
    Activations Density 0.132%

    No Known Activations