© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8146
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "ulate" and its variations, indicating a focus on terms related to processes or functions in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.72
    ItemBackground
    -0.67
    FormTagHelper
    -0.67
     "..\..\..\
    -0.65
     tématu
    -0.61
    erializer
    -0.61
    }\]
    -0.59
    LEncoder
    -0.58
    зулта
    -0.57
     оригіналу
    -0.57
    POSITIVE LOGITS
    ulate
    1.81
    ulation
    1.81
    ulated
    1.80
    ulating
    1.66
    ulates
    1.52
    ulations
    1.36
    ULATION
    1.35
    ULATED
    1.20
    ULATE
    1.09
    ulator
    0.93
    Activations Density 0.085%

    No Known Activations