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. 24-GEMMASCOPE-RES-16K
    6. 1090
    Prev
    Next
    INDEX
    Explanations

    the word "around" and its variants, indicating a focus on surrounding contexts or environments

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

    "around"

    np_acts-logits-general · gemini-2.0-flash

    around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    <bos>
    -0.44
     незавершена
    -0.41
    Trus
    -0.39
    ]})
    -0.39
    )})
    -0.38
     truk
    -0.37
    '))
    -0.35
    Dea
    -0.35
    timewa
    -0.35
    '})
    -0.34
    POSITIVE LOGITS
    around
    1.43
     AROUND
    1.37
    Around
    1.37
     around
    1.36
     Around
    1.31
    AROUND
    1.27
     вокруг
    1.03
     autour
    1.02
     alrededor
    0.95
     omkring
    0.95
    Activations Density 0.077%

    No Known Activations