© 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. 3937
    Prev
    Next
    INDEX
    Explanations

    negative descriptors related to situations or conditions

    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
     GetEnumerator
    -0.57
     trust
    -0.56
    ss
    -0.54
    celot
    -0.53
     Zel
    -0.50
    igshid
    -0.49
     yarar
    -0.48
    spans
    -0.48
    sträger
    -0.47
     kick
    -0.47
    POSITIVE LOGITS
     terrible
    2.20
     awful
    2.14
    terrible
    2.08
     Terrible
    1.99
     horrible
    1.94
    Terrible
    1.75
     dreadful
    1.72
    awful
    1.71
     horrendous
    1.67
     horrid
    1.63
    Activations Density 0.106%

    No Known Activations