© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 13008
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or tasks being completed or obligations being fulfilled

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utilisons
    -0.58
    []>(
    -0.57
    )))),
    -0.56
    lesi
    -0.54
    norsk
    -0.53
    leriyle
    -0.52
    ])))
    -0.52
     ارزش
    -0.51
     Assay
    -0.51
    ="<?=
    -0.51
    POSITIVE LOGITS
     المعيارى
    0.84
     AssemblyTitle
    0.74
     myſelf
    0.69
     Efq
    0.68
    躇
    0.65
    principalTable
    0.63
    WriteTagHelper
    0.61
    RUnlock
    0.58
     BoxDecoration
    0.58
    protoc
    0.57
    Activations Density 0.397%

    No Known Activations