© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 8283
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to conditional checks and object state validation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Бахар
    -0.44
     Spinoza
    -0.41
     inoxydable
    -0.40
    astify
    -0.39
    Autos
    -0.39
    nastics
    -0.38
    lobe
    -0.37
     Mech
    -0.37
    letoe
    -0.37
     Infórmanos
    -0.37
    POSITIVE LOGITS
     null
    1.50
    null
    1.20
     NULL
    1.16
    NULL
    0.97
     nullptr
    0.94
    assertNull
    0.93
    Null
    0.87
     Null
    0.85
    NullException
    0.81
     nil
    0.77
    Activations Density 0.357%

    No Known Activations