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. 16-GEMMASCOPE-RES-16K
    6. 757
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and equations related to statistical estimators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or physics equations/formulae

    np_acts-logits-general · gemini-2.0-flash

    inverse mathematical entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __;
    -0.62
     ujednoznacz
    -0.62
     sánh
    -0.60
    awtextra
    -0.59
    verdi
    -0.58
    sitis
    -0.58
    IntoConstraints
    -0.57
    DebuggerStep
    -0.57
     pitches
    -0.56
    IVEREF
    -0.56
    POSITIVE LOGITS
     inverse
    0.60
    évaluateur
    0.51
    MessageTagHelper
    0.47
     ovaries
    0.47
     relâche
    0.47
    Portail
    0.46
     comunista
    0.46
    mybatisplus
    0.46
     tác
    0.45
    inverse
    0.44
    Activations Density 1.209%

    No Known Activations