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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15649
    Prev
    Next
    INDEX
    Explanations

    keywords related to API definitions and structured data interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 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
    +#+#
    -1.04
     CreateTagHelper
    -0.92
    OGND
    -0.84
    extAlignment
    -0.83
    sizeCache
    -0.83
    RegistryLite
    -0.79
     kaynağından
    -0.79
    richTextPanel
    -0.77
    PhysRevD
    -0.74
     发表于
    -0.74
    POSITIVE LOGITS
    бук
    0.50
    दार
    0.49
     karş
    0.48
    "]];
    0.46
     gange
    0.45
    )();
    0.44
    letar
    0.43
     Dabei
    0.43
     respon
    0.43
    ilte
    0.42
    Activations Density 0.515%

    No Known Activations