© 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. 2-GEMMASCOPE-RES-16K
    6. 6020
    Prev
    Next
    INDEX
    Explanations

    references to failures or shortcomings in performance or compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -0.92
     postIndex
    -0.85
    enumii
    -0.79
    Datuak
    -0.73
    קישורים
    -0.70
     tapete
    -0.69
    athione
    -0.69
    displayquote
    -0.68
     Drapeau
    -0.68
     contemporain
    -0.64
    POSITIVE LOGITS
     auction
    0.72
     failure
    0.66
    Failure
    0.64
     surn
    0.64
     refusal
    0.63
    jaan
    0.62
     differential
    0.58
     instrumental
    0.58
     Failure
    0.58
     duties
    0.55
    Activations Density 0.101%

    No Known Activations