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. 16-GEMMASCOPE-RES-16K
    6. 6464
    Prev
    Next
    INDEX
    Explanations

    descriptions of qualities or attributes, particularly focusing on compliance, efficiency, and effectiveness

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

    ending in "-able," "-ive," "-al," or "-ic"

    np_acts-logits-general · gemini-2.0-flash

    state or manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referenties
    -0.70
    ]<<"
    -0.66
    ]<=
    -0.66
    writerow
    -0.66
    SPATH
    -0.65
    اریخ
    -0.64
     насељу
    -0.64
    --)
    
    -0.64
     Normdatei
    -0.64
    ագրություններ
    -0.64
    POSITIVE LOGITS
     fashion
    0.71
     format
    0.60
     manner
    0.59
    fashion
    0.59
     biçim
    0.57
     alimentaires
    0.56
    Fashion
    0.56
     måte
    0.55
     way
    0.54
    FunctionFlags
    0.53
    Activations Density 0.225%

    No Known Activations