© 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. 24-GEMMASCOPE-RES-16K
    11. 12535
    Prev
    Next
    INDEX
    Explanations

    references to protests and political grievances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows words indicating negativity or opposition

    np_acts-logits-general · gemini-2.0-flash

    negative framing or specific pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    YMMV
    -0.55
    contributors
    -0.51
    MessageTagHelper
    -0.49
    $.}
    -0.48
    addContainerGap
    -0.48
    jspb
    -0.48
    ześnie
    -0.47
    脚注の使い方
    -0.46
    LabelTagHelper
    -0.46
     $__
    -0.46
    POSITIVE LOGITS
     shameless
    0.64
     blackmail
    0.62
     hatched
    0.62
     transfieras
    0.61
     fooling
    0.61
     spoiling
    0.59
     biased
    0.58
    oredCriteria
    0.58
    PreferredItem
    0.57
     illogical
    0.56
    Activations Density 0.160%

    No Known Activations