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. 18-GEMMASCOPE-RES-16K
    6. 1081
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formatting in academic writing

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

    Mathematical expressions ending with commas

    np_acts-logits-general · gemini-2.0-flash

    commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grimes
    -0.55
    rably
    -0.51
    [__
    -0.48
     NavController
    -0.48
     ['$
    -0.47
    TextEditing
    -0.47
    equalsIgnoreCase
    -0.46
    ●●
    -0.46
    '*
    -0.45
     olla
    -0.45
    POSITIVE LOGITS
    المشاركات
    0.81
     resourceCulture
    0.78
     nakalista
    0.77
    </h5>
    0.74
    setVerticalGroup
    0.74
    ]")]
    0.74
    ftagPool
    0.73
     snippetHide
    0.73
    sizeCache
    0.72
    Дереккөздер
    0.72
    Activations Density 0.565%

    No Known Activations