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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 12454
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to user experiences and interactions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.54
     שוליים
    -0.53
    下手
    -0.51
    icordia
    -0.50
    BASELINE
    -0.50
    onAttach
    -0.50
     AppCompatTheme
    -0.49
    /**
    -0.49
    overset
    -0.47
    めでとう
    -0.46
    POSITIVE LOGITS
     experience
    3.28
    experience
    2.78
     Experience
    2.67
     experiences
    2.65
     EXPERIENCE
    2.62
    Experience
    2.60
     expérience
    2.44
     experiencia
    2.32
    experiences
    2.29
    expérience
    2.23
    Activations Density 0.274%

    No Known Activations