Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3252
    Prev
    Next
    INDEX
    Explanations

    phrases related to candidates and their qualifications for political office

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

    about political races and candidates

    np_acts-logits-general · gemini-2.0-flash

    political candidate for office

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.52
     kaynağından
    -0.52
    gdx
    -0.49
     propOrder
    -0.49
    rítica
    -0.47
    الإنجليزية
    -0.46
     drifts
    -0.46
    OGND
    -0.46
    drift
    -0.45
    GEBURTS
    -0.44
    POSITIVE LOGITS
     political
    0.54
     candidate
    0.50
     kandid
    0.46
     candidates
    0.46
     Political
    0.46
     Candidate
    0.45
    Political
    0.44
     elected
    0.44
     candidatura
    0.43
    political
    0.43
    Activations Density 0.304%

    No Known Activations