© 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. 0-GEMMASCOPE-RES-16K
    6. 8799
    Prev
    Next
    INDEX
    Explanations

    explicit language and references to sexual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⟬
    -0.50
    exitRule
    -0.47
    cticut
    -0.42
    termilk
    -0.42
    ultati
    -0.42
    orszá
    -0.41
     ujednoznacz
    -0.39
     vermitteln
    -0.39
     Allí
    -0.39
    VertexArray
    -0.38
    POSITIVE LOGITS
     fucking
    0.74
    fucking
    0.62
     FUCKING
    0.60
    Fucking
    0.59
     Advantage
    0.58
     Fucking
    0.57
     Favor
    0.57
     Conven
    0.57
     &___
    0.54
     advantage
    0.54
    Activations Density 1.570%

    No Known Activations