© 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-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9997
    Prev
    Next
    INDEX
    Explanations

    specific nouns and terms related to natural resources and environmental topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.94
     noDo
    -0.91
    GEBURTSDATUM
    -0.89
     disambiguazione
    -0.85
    ⟬
    -0.83
     يتيمه
    -0.80
     Normdatei
    -0.77
    المكان
    -0.74
     betweenstory
    -0.73
     ExecuteAsync
    -0.73
    POSITIVE LOGITS
    all
    0.41
    IN
    0.40
    trong
    0.40
    A
    0.40
    on
    0.39
     
    0.39
    of
    0.39
    O
    0.39
    tag
    0.39
    alou
    0.38
    Activations Density 8.329%

    No Known Activations