© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 7629
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical decomposition and partitioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Decomposition or breaking down

    np_acts-logits-general · gemini-2.0-flash

    decompose into / to / as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     el
    -0.40
     O
    -0.40
    clude
    -0.39
     Cap
    -0.39
    viation
    -0.39
    ieval
    -0.38
     absolute
    -0.38
    关
    -0.37
    Counters
    -0.37
    ACLE
    -0.37
    POSITIVE LOGITS
     decompose
    1.09
     decomposition
    1.08
     splitting
    1.02
     decomposed
    0.99
    Decomposition
    0.98
     Decomposition
    0.97
     decom
    0.96
     split
    0.95
    decomposition
    0.95
    分解
    0.94
    Activations Density 0.841%

    No Known Activations