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. 27-GEMMASCOPE-RES-16K
    6. 9729
    Prev
    Next
    INDEX
    Explanations

    terms related to payments and financial transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ו
    -0.49
    eyes
    -0.48
    ا
    -0.48
    ax
    -0.47
    odds
    -0.45
    ़
    -0.45
    XmlAccessorType
    -0.44
    épa
    -0.44
    ので
    -0.42
    hydro
    -0.42
    POSITIVE LOGITS
     ब्रेकडाउन
    0.63
    t
    0.57
    dient
    0.54
    lement
    0.54
    ations
    0.54
    dent
    0.54
    dant
    0.54
    ment
    0.53
     Element
    0.52
    IENT
    0.52
    Activations Density 0.751%

    No Known Activations