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. 7-GEMMASCOPE-RES-16K
    6. 15390
    Prev
    Next
    INDEX
    Explanations

    references to various factors or elements that influence outcomes or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abetes
    -0.86
    orgeous
    -0.74
    原始内容存档于
    -0.74
    edicated
    -0.74
    ),),
    -0.70
     Bullock
    -0.66
     submissive
    -0.66
    mime
    -0.66
     contemporaine
    -0.65
     Mahoney
    -0.64
    POSITIVE LOGITS
     factors
    2.07
     Factors
    1.98
    factors
    1.87
     Factor
    1.87
     factor
    1.85
     FACTOR
    1.80
    Factors
    1.78
     FACTORS
    1.75
    factor
    1.71
    Factor
    1.69
    Activations Density 0.144%

    No Known Activations