© 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. 11-GEMMASCOPE-RES-16K
    6. 12966
    Prev
    Next
    INDEX
    Explanations

    elements associated with database cursor operations and dynamic data handling in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.93
    StoreMessageInfo
    -0.67
     itſelf
    -0.66
     utafitiHapana
    -0.65
    DockStyle
    -0.65
     cauſe
    -0.65
     متعلقه
    -0.61
    addComponent
    -0.60
     kasarigan
    -0.60
    Parcelize
    -0.59
    POSITIVE LOGITS
    MockMvc
    0.65
    createStatement
    0.65
    JNIEnv
    0.58
    DataInputStream
    0.56
    bufio
    0.55
    DataOutputStream
    0.55
    PrintWriter
    0.53
    DllImport
    0.52
    setAccessible
    0.51
     useNavigate
    0.51
    Activations Density 0.121%

    No Known Activations