© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9870
    Prev
    Next
    INDEX
    Explanations

    the presence of words related to political associations and actions

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

    actions of readiness

    np_acts-logits-general · gemini-2.0-flash

    preparing for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     konusu
    -0.48
    ortunadamente
    -0.47
    )))));
    -0.47
     cometido
    -0.43
    ोंने
    -0.43
     niềm
    -0.43
    ologique
    -0.43
    enschaft
    -0.41
    Citiți
    -0.41
     Lexicon
    -0.41
    POSITIVE LOGITS
     preparation
    2.48
     preparing
    2.23
     prepare
    2.18
    preparation
    2.18
     prepares
    2.14
     Preparation
    2.10
     preparatory
    2.04
     PREPARATION
    2.00
    Preparation
    1.97
     preparations
    1.97
    Activations Density 0.517%

    No Known Activations