© 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. 21-GEMMASCOPE-RES-16K
    6. 15967
    Prev
    Next
    INDEX
    Explanations

    instances of null values in code or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.51
    XmlAccessorType
    -0.47
    eam
    -0.46
    بوابة
    -0.46
    istra
    -0.46
     AssemblyTitle
    -0.46
    subsubsection
    -0.45
    EC
    -0.45
    */].
    -0.45
    ec
    -0.43
    POSITIVE LOGITS
     null
    1.23
    null
    1.14
     Null
    1.08
     NULL
    0.95
    Null
    0.94
    NullException
    0.85
    NULL
    0.84
    assertNull
    0.79
    isNull
    0.76
    IsNull
    0.71
    Activations Density 0.054%

    No Known Activations