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. 2-GEMMASCOPE-RES-16K
    6. 2141
    Prev
    Next
    INDEX
    Explanations

    functions related to memory allocation and resource management in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.48
    writeString
    -0.48
     TestBed
    -0.47
     dře
    -0.46
    Datuak
    -0.45
    ној
    -0.45
     Walkover
    -0.44
     onData
    -0.43
     Party
    -0.42
    addTab
    -0.42
    POSITIVE LOGITS
     Efq
    1.11
     Majefty
    1.01
     ſeveral
    0.98
     Monfieur
    0.95
     Jefus
    0.94
     greateſt
    0.92
     pleaſure
    0.92
     Anſ
    0.92
     houſe
    0.91
     ſon
    0.90
    Activations Density 0.306%

    No Known Activations