© 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. 4-GEMMASCOPE-RES-16K
    6. 10724
    Prev
    Next
    INDEX
    Explanations

    the concept of neutrality or neutral states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.58
    (
    -0.54
     esclavos
    -0.52
    nd
    -0.51
    …
    -0.51
     convective
    -0.51
     povo
    -0.50
    ว
    -0.50
    ↵
    -0.50
    {
    -0.50
    POSITIVE LOGITS
     neutral
    1.54
     Neutral
    1.47
    UTRAL
    1.45
    neutral
    1.44
    Neutral
    1.38
     neutre
    1.34
     нейтра
    1.30
     neutrals
    1.27
     hurt
    1.25
     neutrality
    1.25
    Activations Density 0.108%

    No Known Activations