© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 5575
    Prev
    Next
    INDEX
    Explanations

    code-related constructs, particularly involving memory management and object initialization in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IMPAC
    -0.41
    Extr
    -0.40
    Impossible
    -0.40
    empor
    -0.40
    Intern
    -0.40
    Inspect
    -0.39
    Implications
    -0.39
    IME
    -0.38
    extr
    -0.37
    inspect
    -0.37
    POSITIVE LOGITS
     init
    2.27
     initi
    2.22
    init
    2.03
     INITI
    1.99
     initialization
    1.98
     Initi
    1.98
     иници
    1.96
     initiative
    1.95
     Init
    1.91
    INIT
    1.90
    Activations Density 0.521%

    No Known Activations