© 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. 2-GEMMASCOPE-RES-16K
    6. 820
    Prev
    Next
    INDEX
    Explanations

    references to state management in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SuppressLint
    -0.69
    "}"
    -0.50
    ByDefault
    -0.49
     cụ
    -0.49
    getchar
    -0.49
    __.__
    -0.48
     suivante
    -0.48
    hã
    -0.48
    UIControlState
    -0.48
    домо
    -0.48
    POSITIVE LOGITS
    state
    1.91
    State
    1.19
    STATE
    1.14
     state
    0.87
     STATE
    0.84
     State
    0.81
    setState
    0.80
    states
    0.73
    getState
    0.70
     estatal
    0.68
    Activations Density 0.139%

    No Known Activations