© 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. 7-GEMMASCOPE-RES-16K
    6. 2868
    Prev
    Next
    INDEX
    Explanations

    terms related to secretive organizations and their influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    instagram
    -0.55
    ătoare
    -0.54
     animals
    -0.52
    ashvili
    -0.51
    igas
    -0.50
     situé
    -0.50
     located
    -0.49
    nice
    -0.49
     dan
    -0.47
     animali
    -0.47
    POSITIVE LOGITS
    脚注の使い方
    0.91
    NameInMap
    0.89
    utnik
    0.86
    KommentareTeilen
    0.84
     كومونز
    0.80
    $")
    0.77
     kaynağından
    0.77
    $",
    0.74
    ()]
    
    0.74
    دانشنامهٔ
    0.74
    Activations Density 0.806%

    No Known Activations