© 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. 4997
    Prev
    Next
    INDEX
    Explanations

    terms related to TH (potentially referencing a specific substance or phenomenon in a scientific context)

    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
    身
    -0.55
     hate
    -0.55
    )]$
    -0.54
    printStackTrace
    -0.54
     }^{*}$
    -0.53
     Татар
    -0.51
    ẢN
    -0.50
    writeFieldEnd
    -0.49
     PROCEED
    -0.49
    hate
    -0.48
    POSITIVE LOGITS
     SH
    1.82
    SH
    1.77
     TH
    1.72
     PH
    1.64
     WH
    1.52
     CH
    1.50
    TH
    1.44
    PH
    1.38
     KH
    1.34
    WH
    1.34
    Activations Density 0.110%

    No Known Activations