© 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. 1497
    Prev
    Next
    INDEX
    Explanations

    concepts related to cognitive processes and their implications on learning and understanding

    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
     OkHttpClient
    -0.61
     Италијани
    -0.60
    createCanvas
    -0.59
    FunctionFlags
    -0.57
    RegressionTest
    -0.57
    getColumnIndex
    -0.57
    %)$
    -0.56
    Tikang
    -0.55
     ActionBar
    -0.54
    writeFieldEnd
    -0.54
    POSITIVE LOGITS
     ideas
    1.02
     events
    0.90
     phenomena
    0.86
     concepts
    0.86
     meaning
    0.83
    ideas
    0.80
     ideias
    0.79
     idées
    0.76
     thoughts
    0.74
     experiences
    0.72
    Activations Density 0.607%

    No Known Activations