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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 2936
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of the word "trouble" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]]=
    -0.45
    évaluateur
    -0.44
    setLayoutManager
    -0.42
     exhausting
    -0.42
     باخ
    -0.40
     outdated
    -0.40
    invokeLater
    -0.40
     Audiodateien
    -0.40
    DockStyle
    -0.40
    Beijos
    -0.39
    POSITIVE LOGITS
     trouble
    2.86
    trouble
    2.47
     troubles
    2.45
     Trouble
    2.42
    Trouble
    2.39
     problem
    2.22
    problem
    2.06
     Problem
    1.91
     Troubles
    1.90
    Problem
    1.89
    Activations Density 0.260%

    No Known Activations