© 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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8211
    Prev
    Next
    INDEX
    Explanations

    technical terminology and concepts related to neural networks and algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Input" or "inputs" and related words

    np_acts-logits-general · gemini-2.0-flash

    input or inputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EntityFramework
    -0.34
    CRL
    -0.32
    Chham
    -0.30
    ScopeManager
    -0.30
     azon
    -0.29
    arti
    -0.29
    migrationBuilder
    -0.29
     CRL
    -0.28
     Giants
    -0.28
     אח
    -0.28
    POSITIVE LOGITS
     input
    1.79
     inputs
    1.64
     Input
    1.55
     INPUT
    1.47
     Inputs
    1.46
    input
    1.46
    Input
    1.38
    INPUT
    1.37
    输入
    1.32
     getInput
    1.32
    Activations Density 0.997%

    No Known Activations