© 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. 36-GEMMASCOPE-RES-16K
    11. 16061
    Prev
    Next
    INDEX
    Explanations

    relationships or connections between entities in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -1.13
     autorytatywna
    -0.98
     queſta
    -0.94
     betweenstory
    -0.91
     ſind
    -0.89
    OGND
    -0.87
    باردا
    -0.85
    IntoConstraints
    -0.85
     $_(
    -0.85
    ロウィン
    -0.85
    POSITIVE LOGITS
    )
    0.80
    ()
    0.65
    ”
    0.59
    }
    0.59
    ]
    0.58
    "
    0.50
    」
    0.47
    »
    0.46
    ")
    0.42
    ')
    0.37
    Activations Density 0.719%

    No Known Activations