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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 7940
    Prev
    Next
    INDEX
    Explanations

    interactions and dialogues involving family members and personal relationships

    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
     vermag
    -0.65
     obtaining
    -0.63
     occurring
    -0.62
     residing
    -0.62
     אשר
    -0.62
     possessing
    -0.61
     sahiptir
    -0.61
     utilising
    -0.60
     viewing
    -0.59
     pertanto
    -0.59
    POSITIVE LOGITS
     said
    0.76
     fucked
    0.69
     freaked
    0.67
     told
    0.67
     got
    0.65
     SAID
    0.64
     talked
    0.63
     kinda
    0.63
     figured
    0.63
     thought
    0.62
    Activations Density 0.374%

    No Known Activations