© 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. 15-GEMMASCOPE-RES-16K
    6. 1397
    Prev
    Next
    INDEX
    Explanations

    structural elements and data related to figures and errors in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SuppressLint
    -0.68
    
    -0.54
     Whelan
    -0.53
    
    -0.51
    DllImport
    -0.51
    EqualsAnd
    -0.49
    Enciclopedia
    -0.46
    arraycopy
    -0.44
    liferay
    -0.43
    ChromeDriver
    -0.43
    POSITIVE LOGITS
     religieuses
    0.72
    findpost
    0.71
     varandra
    0.59
     Quod
    0.59
     continúas
    0.58
    posables
    0.58
    Demografía
    0.57
     skydd
    0.56
     picioare
    0.56
     quæ
    0.55
    Activations Density 0.057%

    No Known Activations