© 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. 1-GEMMASCOPE-RES-16K
    6. 15168
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liesslich
    -0.54
     Generale
    -0.53
    impianto
    -0.53
    {§
    -0.53
     }}"></
    -0.52
     purpoſe
    -0.52
    qvarna
    -0.52
     ".";
    -0.49
     '.';
    -0.49
    oğlu
    -0.49
    POSITIVE LOGITS
    SourceChecksum
    0.94
    mybatisplus
    0.88
     propOrder
    0.82
    ThroughAttribute
    0.80
    DebuggerStep
    0.79
    GEBURTSDATUM
    0.78
    ChildScrollView
    0.78
    messageInfo
    0.77
    IUrlHelper
    0.76
    parsedMessage
    0.75
    Activations Density 2.186%

    No Known Activations