© 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. 10604
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to 3D graphics and lighting in programming

    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
     crackling
    -0.62
     pinulongan
    -0.54
    Sklici
    -0.53
    PyExc
    -0.52
     Lak
    -0.52
    ReusableCell
    -0.50
    execSQL
    -0.49
    HtmlAttribute
    -0.48
    ignac
    -0.47
     vibration
    -0.46
    POSITIVE LOGITS
     camera
    1.08
     Camera
    0.99
    camera
    0.98
    Camera
    0.92
     cameras
    0.88
    Perspective
    0.88
     CAMERA
    0.86
     Perspective
    0.84
     Cameras
    0.84
     perspective
    0.83
    Activations Density 0.424%

    No Known Activations