© 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. 25-GEMMASCOPE-RES-16K
    6. 12800
    Prev
    Next
    INDEX
    Explanations

    explicit expressions of sexual interactions and related dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tbh
    -0.53
    bVar
    -0.51
     visiting
    -0.48
    Lors
    -0.48
     visits
    -0.48
    andina
    -0.46
    peteer
    -0.46
    ebenarnya
    -0.45
     πραγ
    -0.45
    iostream
    -0.45
    POSITIVE LOGITS
     Hurry
    0.90
     hurry
    0.89
     Come
    0.88
    Come
    0.83
     come
    0.83
     Get
    0.81
     COME
    0.78
    Hurry
    0.76
    come
    0.76
     GET
    0.74
    Activations Density 0.305%

    No Known Activations