© 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. 10-GEMMASCOPE-RES-16K
    11. 15480
    Prev
    Next
    INDEX
    Explanations

    key phrases related to measurement and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perchè
    -0.76
    +#+#
    -0.75
    UnusedPrivate
    -0.68
     loosing
    -0.63
    ChildScrollView
    -0.60
     poichè
    -0.60
    ="@+
    -0.60
    
    -0.58
    Composable
    -0.57
    ]=>
    -0.57
    POSITIVE LOGITS
     nonnegative
    0.60
     –,
    0.58
     به‌عنوان
    0.57
     État
    0.56
    ​—
    0.53
    ,’”
    0.52
    更好地
    0.50
     derselben
    0.50
     —,
    0.49
    État
    0.48
    Activations Density 2.571%

    No Known Activations