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. 12-GEMMASCOPE-RES-16K
    6. 11992
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial analysis questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.51
     sowieso
    -0.49
    rawQuery
    -0.47
     вроде
    -0.46
     ohnehin
    -0.46
     acknowledged
    -0.46
    <sup>
    -0.46
     gefe
    -0.45
     cioè
    -0.45
    <u>
    -0.44
    POSITIVE LOGITS
     '\\;'
    0.89
    nemia
    0.65
    ulite
    0.65
    SBATCH
    0.64
     Vou
    0.63
    raulic
    0.62
    uxxxx
    0.61
     NUKAT
    0.61
    bells
    0.60
     OMITBAD
    0.60
    Activations Density 1.131%

    No Known Activations