© 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. 2-GEMMASCOPE-RES-16K
    6. 7026
    Prev
    Next
    INDEX
    Explanations

    instances of specific bracket or brace characters

    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
    subplots
    -0.77
     Athe
    -0.71
    ReusableCell
    -0.66
    HasForeignKey
    -0.66
    archiviato
    -0.65
    HostException
    -0.64
    nodoc
    -0.62
     lateinit
    -0.60
     externi
    -0.58
    الدراسه
    -0.58
    POSITIVE LOGITS
    <h2>
    1.36
    <h3>
    1.09
    <h1>
    1.01
    <strong>
    0.98
    <b>
    0.98
    <h4>
    0.97
     }));
    0.92
    <h5>
    0.92
    ())));
    0.91
    "}}>
    0.84
    Activations Density 0.058%

    No Known Activations