© 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. 21-GEMMASCOPE-RES-16K
    6. 14016
    Prev
    Next
    INDEX
    Explanations

    phrases related to online presence and search visibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.64
    stdc
    -0.58
     AssemblyCompany
    -0.58
    CompleteListener
    -0.57
     resourceCulture
    -0.56
    Demografie
    -0.51
     détermination
    -0.51
     Interpretation
    -0.50
    Significado
    -0.49
     decidi
    -0.49
    POSITIVE LOGITS
     mention
    2.90
     mentions
    2.54
     Mention
    2.37
     mentioned
    2.34
     mentioning
    2.34
     references
    2.29
     reference
    2.27
    mention
    2.24
    Mention
    2.19
     referenced
    2.04
    Activations Density 0.671%

    No Known Activations