© 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. 3282
    Prev
    Next
    INDEX
    Explanations

    mechanical components and their interactions in systems

    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
    merkungen
    -0.65
    RegressionTest
    -0.60
     Roskov
    -0.57
     оригіналу
    -0.57
    SequentialGroup
    -0.57
    RenderAtEndOf
    -0.55
    VersionUID
    -0.53
    Trama
    -0.53
    siasi
    -0.51
     perus
    -0.51
    POSITIVE LOGITS
     horizontally
    0.92
     laterally
    0.89
     vertically
    0.88
     sideways
    0.83
     outward
    0.81
     backward
    0.78
     backwards
    0.78
     diagonally
    0.78
     upwards
    0.76
     outwards
    0.76
    Activations Density 0.686%

    No Known Activations