Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 81499
    Prev
    Next
    INDEX
    Explanations

    control flow structures and punctuation in programming code

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

    maven plugins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createState
    -0.79
     betweenstory
    -0.71
    Autoritní
    -0.63
    AxisAlignment
    -0.55
    MemoryWarning
    -0.55
    HasBeenSet
    -0.51
    MethodManager
    -0.50
     MainAxisSize
    -0.49
     hashlib
    -0.46
    WaitGroup
    -0.46
    POSITIVE LOGITS
    حوالہ
    0.55
     sahip
    0.40
    ptonshire
    0.39
     skär
    0.38
    endaftaran
    0.37
     inti
    0.36
    Rafael
    0.36
     punte
    0.35
     Raquel
    0.35
     zamanda
    0.35
    Activations Density 0.061%

    No Known Activations