© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7185
    Prev
    Next
    INDEX
    Explanations

    references to trustworthiness and the concept of upper vs lower categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ‚¬
    -0.66
    ########.
    -0.62
     COA
    -0.62
    WriteLiteral
    -0.60
    endforeach
    -0.60
    __':
    -0.59
    memoized
    -0.59
    toyage
    -0.58
    <()>
    -0.57
     scp
    -0.56
    POSITIVE LOGITS
     trusted
    1.00
     trust
    0.89
     trusting
    0.78
    trusted
    0.77
     trusts
    0.74
    trust
    0.72
     populated
    0.66
     Upper
    0.63
     Dense
    0.61
    Lower
    0.59
    Activations Density 0.154%

    No Known Activations