© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 123168
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters in text

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

    special characters and code tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vœ
    -0.45
     avoient
    -0.39
     pouvoit
    -0.39
     þat
    -0.36
     debout
    -0.35
    Especificación
    -0.34
     Abonnez
    -0.33
     Inscrivez
    -0.32
    impanan
    -0.32
     constitucional
    -0.32
    POSITIVE LOGITS
    ]")]
    0.59
     })}
    0.58
    tifies
    0.57
    enderror
    0.57
    DTD
    0.56
    
    
    0.55
    StoreMessageInfo
    0.55
     >=",
    0.55
    apos
    0.53
    </>
    
    0.53
    Activations Density 0.192%

    No Known Activations