© 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. 25-GEMMASCOPE-RES-16K
    6. 8308
    Prev
    Next
    INDEX
    Explanations

    technical terms and descriptive phrases related to machinery and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    িনি
    -0.65
     YOURSELF
    -0.63
    addCriterion
    -0.61
    themselves
    -0.60
    yourself
    -0.60
    TypedDataSet
    -0.58
     beliau
    -0.58
    simus
    -0.58
     ایشان
    -0.56
    nextDouble
    -0.56
    POSITIVE LOGITS
     its
    4.72
    Its
    3.41
     Its
    3.31
    its
    3.18
    它的
    2.64
     Оно
    2.07
    其
    2.04
     ITS
    1.90
     suoi
    1.84
    它
    1.81
    Activations Density 3.268%

    No Known Activations